The ade4 Package - NexTag Supports Open Source Initiatives
The ade4 Package - NexTag Supports Open Source Initiatives
The ade4 Package - NexTag Supports Open Source Initiatives
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
<strong>The</strong> <strong>ade4</strong> <strong>Package</strong><br />
February 16, 2008<br />
Version 1.4-5<br />
Date 2007/10/12<br />
Title Analysis of Ecological Data : Exploratory and Euclidean methods in Environmental sciences<br />
Author Daniel Chessel, Anne-Beatrice Dufour and Stephane Dray<br />
, with contributions from Jean R. Lobry, Sebastien Ollier,<br />
Sandrine Pavoine and Jean Thioulouse.<br />
Maintainer Simon Penel <br />
Suggests waveslim, splancs, MASS, maptools, spdep, pixmap, ape, tripack, <strong>ade4</strong>TkGUI<br />
Description Multivariate data analysis and graphical display.<br />
License GPL version 2 or newer<br />
URL http://pbil.univ-lyon1.fr/ADE-4, Mailing list: http://listes.univ-lyon1.fr/wws/info/adelist<br />
R topics documented:<br />
EH . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7<br />
PI2newick . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8<br />
RV.rtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9<br />
RVdist.randtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10<br />
abouheif.eg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10<br />
acacia . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11<br />
add.scatter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12<br />
<strong>ade4</strong>toR . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14<br />
aminoacyl . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16<br />
amova . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17<br />
apis108 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18<br />
ardeche . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19<br />
area.plot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20<br />
arrival . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23<br />
as.taxo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24<br />
atlas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25<br />
1
2 R topics documented:<br />
atya . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26<br />
avijons . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27<br />
avimedi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29<br />
aviurba . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30<br />
bacteria . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31<br />
banque . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32<br />
baran95 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33<br />
between . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35<br />
bf88 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36<br />
bicenter.wt . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37<br />
bordeaux . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38<br />
bsetal97 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38<br />
buech . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40<br />
butterfly . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41<br />
cailliez . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42<br />
capitales . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43<br />
carni19 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44<br />
carni70 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44<br />
carniherbi49 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45<br />
casitas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46<br />
cca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47<br />
chatcat . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49<br />
chats . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50<br />
chazeb . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51<br />
chevaine . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51<br />
clementines . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52<br />
cnc2003 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53<br />
coinertia . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55<br />
coleo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57<br />
corkdist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58<br />
corvus . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59<br />
deug . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60<br />
disc . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61<br />
discrimin . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62<br />
discrimin.coa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63<br />
dist.binary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64<br />
dist.dudi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65<br />
dist.genet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66<br />
dist.neig . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68<br />
dist.prop . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69<br />
dist.quant . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 70<br />
divc . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 72<br />
divcmax . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 73<br />
dotchart.phylog . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 74<br />
dotcircle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76<br />
doubs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77<br />
dpcoa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78<br />
dudi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80
R topics documented: 3<br />
dudi.acm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81<br />
dudi.coa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83<br />
dudi.dec . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84<br />
dudi.fca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 85<br />
dudi.hillsmith . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 87<br />
dudi.mix . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 88<br />
dudi.nsc . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 90<br />
dudi.pca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 91<br />
dudi.pco . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 92<br />
dunedata . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94<br />
ecg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 95<br />
ecomor . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 96<br />
elec88 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 97<br />
escopage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 99<br />
euro123 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 99<br />
fission . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 100<br />
foucart . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 101<br />
friday87 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103<br />
fruits . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103<br />
fuzzygenet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 105<br />
gearymoran . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 106<br />
genet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 107<br />
ggtortoises . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 110<br />
granulo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111<br />
gridrowcol . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 112<br />
hdpg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113<br />
housetasks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 114<br />
humDNAm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 115<br />
ichtyo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 116<br />
inertia.dudi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 117<br />
irishdata . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 118<br />
is.euclid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 119<br />
julliot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 120<br />
jv73 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 122<br />
kcponds . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 123<br />
kdist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 124<br />
kdist2ktab . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 126<br />
kdisteuclid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 127<br />
kplot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 129<br />
kplot.foucart . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 129<br />
kplot.mcoa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 130<br />
kplot.mfa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 131<br />
kplot.pta . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 132<br />
kplot.sepan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 133<br />
kplot.statis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 135<br />
krandtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 136<br />
ktab . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 137<br />
ktab.data.frame . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 139
4 R topics documented:<br />
ktab.list.df . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 140<br />
ktab.list.dudi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 141<br />
ktab.match2ktabs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 142<br />
ktab.within . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 143<br />
lascaux . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 144<br />
lingoes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 145<br />
lizards . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 146<br />
macaca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 147<br />
macon . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 148<br />
mafragh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 148<br />
mantel.randtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 149<br />
mantel.rtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 150<br />
maples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 151<br />
mariages . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 152<br />
mcoa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 153<br />
meau . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 155<br />
meaudret . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 156<br />
mfa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 157<br />
microsatt . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 158<br />
mjrochet . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 160<br />
mld . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 161<br />
mollusc . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 162<br />
monde84 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 163<br />
morphosport . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 164<br />
mstree . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 165<br />
multispati . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 166<br />
multispati.randtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 169<br />
multispati.rtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 170<br />
neig . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 171<br />
newick.eg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 174<br />
newick2phylog . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 175<br />
niche . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 177<br />
njplot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 179<br />
olympic . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 180<br />
optimEH . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 181<br />
oribatid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 182<br />
originality . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 183<br />
orisaved . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 185<br />
orthobasis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 186<br />
orthogram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 189<br />
ours . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 191<br />
palm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 193<br />
pap . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 194<br />
pcaiv . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 195<br />
pcaivortho . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 196<br />
pcoscaled . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 198<br />
perthi02 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 199<br />
phylog . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 200
R topics documented: 5<br />
plot.phylog . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 202<br />
presid2002 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 205<br />
procella . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 206<br />
procuste . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 207<br />
procuste.randtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 209<br />
procuste.rtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 210<br />
pta . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 211<br />
quasieuclid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 213<br />
randEH . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 214<br />
randtest-internal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 215<br />
randtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 216<br />
randtest.amova . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 217<br />
randtest.between . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 218<br />
randtest.coinertia . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 219<br />
randtest.discrimin . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 220<br />
rankrock . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 221<br />
reconst . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 221<br />
rhone . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 223<br />
rlq . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 224<br />
rpjdl . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 226<br />
rtest . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 227<br />
rtest.between . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 228<br />
rtest.discrimin . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 229<br />
s.arrow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 230<br />
s.chull . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 231<br />
s.class . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 233<br />
s.corcircle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 235<br />
s.distri . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 236<br />
s.hist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 238<br />
s.image . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 239<br />
s.kde2d . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 241<br />
s.label . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 242<br />
s.logo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 244<br />
s.match . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 246<br />
s.multinom . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 247<br />
s.traject . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 249<br />
s.value . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 251<br />
santacatalina . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 253<br />
sarcelles . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 254<br />
scalewt . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 255<br />
scatter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 256<br />
scatter.acm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 258<br />
scatter.coa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 258<br />
scatter.dudi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 259<br />
scatter.fca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 261<br />
sco.boxplot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 262<br />
sco.distri . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 263<br />
sco.quant . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 264
6 R topics documented:<br />
score . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 265<br />
score.acm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 266<br />
score.coa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 267<br />
score.mix . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 269<br />
score.pca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 270<br />
seconde . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 271<br />
sepan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 271<br />
skulls . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 273<br />
statis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 274<br />
steppe . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 275<br />
supcol . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 276<br />
suprow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 277<br />
symbols.phylog . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 279<br />
syndicats . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 280<br />
t3012 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 280<br />
table.cont . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 281<br />
table.dist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 282<br />
table.paint . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 283<br />
table.phylog . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 284<br />
table.value . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 285<br />
tarentaise . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 286<br />
taxo.eg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 288<br />
testdim . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 289<br />
tintoodiel . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 290<br />
tithonia . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 291<br />
tortues . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 292<br />
toxicity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 293<br />
triangle.class . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 294<br />
triangle.plot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 295<br />
trichometeo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 297<br />
ungulates . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 298<br />
uniquewt.df . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 299<br />
variance.phylog . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 300<br />
vegtf . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 301<br />
veuvage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 302<br />
westafrica . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 303<br />
within . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 305<br />
withinpca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 307<br />
witwit.coa . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 308<br />
worksurv . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 309<br />
yanomama . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 310<br />
zealand . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 311<br />
Index 313
EH 7<br />
EH<br />
Amount of Evolutionary History<br />
Description<br />
computes the sum of branch lengths on an ultrametric phylogenetic tree.<br />
Usage<br />
EH(phyl, select = NULL)<br />
Arguments<br />
phyl<br />
select<br />
an object of class phylog<br />
a vector containing the numbers of the leaves (species) which must be considered<br />
in the computation of the amount of Evolutionary History. This parameter<br />
allows the calculation of the amount of Evolutionary History for a subset of<br />
species.<br />
Value<br />
returns a real value.<br />
Author(s)<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉<br />
References<br />
Nee, S. and May, R.M. (1997) Extinction and the loss of evolutionary history. Science, 278, 692–<br />
694.<br />
Examples<br />
data(carni70)<br />
carni70.phy
8 PI2newick<br />
PI2newick<br />
Import data files from Phylogenetic Independance <strong>Package</strong><br />
Description<br />
This function ensures to transform a data set written for the Phylogenetic Independance package of<br />
Abouheif (1999) in a data set formatting for the functions of <strong>ade4</strong>.<br />
Usage<br />
PI2newick(x)<br />
Arguments<br />
x<br />
is a data frame that contains information on phylogeny topology and trait values<br />
Value<br />
Returns a list containing :<br />
tre<br />
trait<br />
: a character string giving the phylogenetic tree in Newick format<br />
: a vector containing values of the trait<br />
Author(s)<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
Daniel Chessel<br />
References<br />
Abouheif, E. (1999) A method for testing the assumption of phylogenetic independence in comparative<br />
data. Evolutionary Ecology Research, 1, 895–909.<br />
Examples<br />
x
RV.rtest 9<br />
RV.rtest<br />
Monte-Carlo Test on the sum of eigenvalues of a co-inertia analysis<br />
(in R).<br />
Description<br />
performs a Monte-Carlo Test on the sum of eigenvalues of a co-inertia analysis.<br />
Usage<br />
RV.rtest(df1, df2, nrepet = 99)<br />
Arguments<br />
df1, df2<br />
nrepet<br />
two data frames with the same rows<br />
the number of permutations<br />
Value<br />
returns a list of class ’rtest’<br />
Author(s)<br />
Daniel Chessel<br />
References<br />
Heo, M. & Gabriel, K.R. (1997) A permutation test of association between configurations by means<br />
of the RV coefficient. Communications in Statistics - Simulation and Computation, 27, 843-856.<br />
Examples<br />
data(doubs)<br />
pca1
10 abouheif.eg<br />
RVdist.randtest<br />
Tests of randomization on the correlation between two distance matrices<br />
(in R).<br />
Description<br />
performs a RV Test between two distance matrices.<br />
Usage<br />
RVdist.randtest(m1, m2, nrepet = 999)<br />
Arguments<br />
m1, m2 two Euclidean matrices<br />
nrepet the number of permutations<br />
Value<br />
returns a list of class ’randtest’<br />
Author(s)<br />
Daniel Chessel<br />
References<br />
Heo, M. & Gabriel, K.R. (1997) A permutation test of association between configurations by means<br />
of the RV coefficient. Communications in Statistics - Simulation and Computation, 27, 843-856.<br />
Examples<br />
abouheif.eg<br />
Phylogenies and quantitative traits from Abouheif<br />
Description<br />
This data set gathers three phylogenies with three sets of traits as reported by Abouheif (1999).<br />
Usage<br />
data(abouheif.eg)
acacia 11<br />
Format<br />
abouheif.eg is a list containing the 6 following objects :<br />
tre1 is a character string giving the first phylogenetic tree made up of 8 leaves.<br />
vec1 is a numeric vector with 8 values.<br />
tre2 is a character string giving the second phylogenetic tree made up of 7 leaves.<br />
vec2 is a numeric vector with 7 values.<br />
tre3 is a character string giving the third phylogenetic tree made up of 15 leaves.<br />
vec3 is a numeric vector with 15 values.<br />
<strong>Source</strong><br />
Data taken from the phylogenetic independence program developped by Ehab Abouheif starting<br />
from http://ww2.mcgill.ca/biology/faculty/abouheif/programs.html.<br />
References<br />
Abouheif, E. (1999) A method for testing the assumption of phylogenetic independence in comparative<br />
data. Evolutionary Ecology Research, 1, 895–909.<br />
Examples<br />
data(abouheif.eg)<br />
par(mfrow=c(2,2))<br />
symbols.phylog(newick2phylog(abouheif.eg$tre1), abouheif.eg$vec1,<br />
sub = "Body Mass (kg)", csi = 2, csub = 2)<br />
symbols.phylog(newick2phylog(abouheif.eg$tre2), abouheif.eg$vec2,<br />
sub = "Body Mass (kg)", csi = 2, csub = 2)<br />
dotchart.phylog(newick2phylog(abouheif.eg$tre1), abouheif.eg$vec1,<br />
sub = "Body Mass (kg)", cdot = 2, cnod = 1, possub = "topleft",<br />
csub = 2, ceti = 1.5)<br />
dotchart.phylog(newick2phylog(abouheif.eg$tre2), abouheif.eg$vec2,<br />
sub = "Body Mass (kg)", cdot = 2, cnod = 1, possub = "topleft",<br />
csub = 2, ceti = 1.5)<br />
par(mfrow = c(1,1))<br />
w.phy=newick2phylog(abouheif.eg$tre3)<br />
dotchart.phylog(w.phy,abouheif.eg$vec3, clabel.n = 1)<br />
acacia<br />
Spatial pattern analysis in plant communities<br />
Description<br />
Counts of individuals of Acacia ehrenbergiana from five parallel transects of 32 quadrats.
12 add.scatter<br />
Usage<br />
data(acacia)<br />
Format<br />
acacia is a data frame with 15 variables :<br />
se.T1, se.T2, se.T3, se.T4, se.T5 are five numeric vectors containing quadrats counts of seedlings<br />
from transects 1 to 5 respectively;<br />
sm.T1, sm.T2, sm.T3, sm.T4, sm.T5 are five numeric vectors containing quadrats counts of small<br />
trees (crown < 1 m 2 in canopy) of transects 1 to 5 respectively;<br />
la.T1, la.T2, la.T3, la.T4, la.T5 are five numeric vectors containing quadrats counts of trees with<br />
large crown (crown > 1 m 2 in canopy) of transects 1 to 5 respectively.<br />
<strong>Source</strong><br />
Greig-Smith, P. and Chadwick, M.J. (1965) Data on pattern within plant communities. III. Acacia-<br />
Capparis semi-desert scrub in the Sudan. Journal of Ecology, 53, 465–474.<br />
References<br />
Hill, M.O. (1973) <strong>The</strong> intensity of spatial pattern in plant communities. Journal of Ecology, 61,<br />
225–235.<br />
Examples<br />
data(acacia)<br />
par(mfcol = c(5,3))<br />
par(mar = c(2,2,2,2))<br />
for(k in 1:15) {<br />
barplot(acacia[,k], ylim = c(0,20), col = grey(0.8))<br />
scatterutil.sub(names(acacia)[k], 1.5, "topleft")<br />
}<br />
par(mfcol = c(1,1))<br />
add.scatter<br />
Add graphics to an existing plot<br />
Description<br />
add.scatter is a function which defines a new plot area within an existing plot and displays<br />
an additional graphicinside this area. <strong>The</strong> additional graphic is determined by a function which is<br />
the first argument taken by add.scatter. It can be used in various ways, for instance to add a<br />
screeplot to an ordination scatterplot (add.scatter.eig).<br />
<strong>The</strong> function add.scatter.eig uses the following colors: black (represented axes), grey(axes<br />
retained in the analysis) and white (others).
add.scatter 13<br />
Usage<br />
add.scatter(func,posi=c("bottomleft","bottomright","topleft","topright"),ratio=.2,i<br />
add.scatter.eig(w,nf=NULL, xax, yax, posi = "bottomleft", ratio = .25, inset = .01,<br />
Arguments<br />
func<br />
posi<br />
ratio<br />
inset<br />
bg.col<br />
w<br />
nf<br />
xax<br />
yax<br />
sub<br />
csub<br />
an - evaluated - function producing a graphic<br />
a character vector (only its first element being considered) giving the position of<br />
the added graph. Possible values are "bottomleft" (="bottom"),"bottomright","topleft"<br />
(="top"),"topright", and "none" (no plot).<br />
the size of the added graph in proportion of the current plot region<br />
the inset from which the graph is drawn, in proportion of the whole plot region.<br />
Can be a vector of length 2, giving the inset in x and y. If atomic, same inset is<br />
used in x and y<br />
the color of the background of the added graph<br />
numeric vector of eigenvalues<br />
the number of retained factors, NULL if not provided<br />
first represented axis<br />
second represented axis<br />
title of the screeplot<br />
size of the screeplot title<br />
Details<br />
add.scatter uses par("plt") to redefine the new plot region. As stated in par documentation,<br />
this produces to (sometimes surprising) interactions with other parameters such as "mar".<br />
In particular, such interactions are likely to reset the plot region by default which would cause the<br />
additional graphic to take the whole plot region. To avoid such inconvenient, add par([other<br />
options], plt=par("plt")) when using par in your graphical function (argument func).<br />
Value<br />
<strong>The</strong> matched call (invisible).<br />
Author(s)<br />
Thibaut Jombart 〈jombart@biomserv.univ-lyon1.fr〉<br />
See Also<br />
scatter
14 <strong>ade4</strong>toR<br />
Examples<br />
par(mfrow=c(2,2))<br />
f1
<strong>ade4</strong>toR 15<br />
Arguments<br />
fictab<br />
ficcolnames<br />
ficrownames<br />
x<br />
a name of ADE4 text file. A data frame with the same name is created in the R<br />
environment.<br />
the column names label file<br />
the row names label file<br />
a data frame<br />
Details<br />
"xxx" is the name of object x ((deparse(substitute(x))))<br />
For any table :<br />
creates a file "xxx.txt"<br />
creates a file "xxx_row_lab.txt" with row names<br />
creates a file "xxx_col_lab.txt" with column names<br />
if x has the ’col.blocks’ attribute<br />
creates a file "xxx_col_bloc_lab.txt" with blocks names<br />
creates a file "xxx_col_bloc.txt" with blocks sizes<br />
For a table which all columns are factors :<br />
creates a file "xxx.txt"<br />
creates a file "xxx_var_lab.txt" with row names<br />
creates a file "xxx_moda_lab.txt" with categories names<br />
Value<br />
Files are created in the current working directory.<br />
’<strong>ade4</strong>toR’ gives data frames.<br />
’Rto<strong>ade4</strong>’ gives text files.<br />
Examples<br />
data(tarentaise)<br />
traits
16 aminoacyl<br />
aminoacyl<br />
Codon usage<br />
Description<br />
aminoacyl is a list containing the codon counts of 36 genes encoding yeast aminoacyl-tRNAsynthetase(S.Cerevisiae).<br />
Usage<br />
data(aminoacyl)<br />
Format<br />
aminoacyl is a list containing the 5 following objects:<br />
genes is a vector giving the gene names.<br />
localisation is a vector giving the cellular localisation of the proteins (M = mitochondrial, C =<br />
cytoplasmic, I = indetermined, CI = cyto and mito).<br />
codon is a vector containing the 64 triplets.<br />
AA is a factor giving the amino acid names for each codon.<br />
usage.codon is a dataframe containing the codon counts for each gene.<br />
<strong>Source</strong><br />
Data prepared by D. Charif 〈charif@biomserv.univ-lyon1.fr〉 starting from:<br />
http://www.expasy.org/sprot/<br />
References<br />
Chiapello H., Olivier E., Landes-Devauchelle C., Nitschké P. and Risler J.L (1999) Codon usage<br />
as a tool to predict the cellular localisation of eukariotic ribosomal proteins and aminoacyl-tRNA<br />
synthetases. Nucleic Acids Res., 27, 14, 2848–2851.<br />
Examples<br />
data(aminoacyl)<br />
aminoacyl$genes<br />
aminoacyl$usage.codon<br />
dudi.coa(aminoacyl$usage.codon, scannf = FALSE)
amova 17<br />
amova<br />
Analysis of molecular variance<br />
Description<br />
<strong>The</strong> analysis of molecular variance tests the differences among population and/or groups of populations<br />
in a way similar to ANOVA. It includes evolutionary distances among alleles.<br />
Usage<br />
amova(samples, distances, structures)<br />
## S3 method for class 'amova':<br />
print(x, full = FALSE, ...)<br />
Arguments<br />
samples<br />
distances<br />
structures<br />
x<br />
full<br />
a data frame with haplotypes (or genotypes) as rows, populations as columns<br />
and abundance as entries<br />
an object of class dist computed from Euclidean distance. If distances is<br />
null, equidistances are used.<br />
a data frame containing, in the jth row and the kth column, the name of the group<br />
of level k to which the jth population belongs<br />
an object of class amova<br />
a logical value indicating whether the original data (’distances’, ’samples’, ’structures’)<br />
should be printed<br />
... further arguments passed to or from other methods<br />
Value<br />
Returns a list of class amova<br />
call<br />
results<br />
call<br />
a data frame with the degrees of freedom, the sums of squares, and the mean<br />
squares. Rows represent levels of variability.<br />
componentsofcovariance<br />
a data frame containing the components of covariance and their contribution to<br />
the total covariance<br />
statphi<br />
a data frame containing the phi-statistics<br />
Author(s)<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉
18 apis108<br />
References<br />
Excoffier, L., Smouse, P.E. and Quattro, J.M. (1992) Analysis of molecular variance inferred from<br />
metric distances among DNA haplotypes: application to human mitochondrial DNA restriction<br />
data. Genetics, 131, 479–491.<br />
See Also<br />
randtest.amova<br />
Examples<br />
data(humDNAm)<br />
amovahum
ardeche 19<br />
ardeche<br />
Fauna Table with double (row and column) partitioning<br />
Description<br />
This data set gives information about species of benthic macroinvertebrates in different sites and<br />
dates.<br />
Usage<br />
data(ardeche)<br />
Format<br />
ardeche is a list with 6 components.<br />
tab is a data frame containing fauna table with 43 species (rows) and 35 samples (columns).<br />
col.blocks is a vector containing the repartition of samples for the 6 dates : july 1982, august 1982,<br />
november 1982, february 1983, april 1983 and july 1983.<br />
row.blocks is a vector containing the repartition of species in the 4 groups defining the species<br />
order.<br />
dat.fac is a date factor for samples (6 dates).<br />
sta.fac is a site factor for samples (6 sites).<br />
esp.fac is a species order factor (Ephemeroptera, Plecoptera, Coleoptera, Trichoptera).<br />
Details<br />
<strong>The</strong> columns of the data frame ardeche$tab define the samples by a number between 1 and 6<br />
(the date) and a letter between A and F (the site).<br />
<strong>Source</strong><br />
Cazes, P., Chessel, D., and Dolédec, S. (1988) L’analyse des correspondances internes d’un tableau<br />
partitionné : son usage en hydrobiologie. Revue de Statistique Appliquée, 36, 39–54.<br />
Examples<br />
data(ardeche)<br />
dudi1
20 area.plot<br />
area.plot<br />
Graphical Display of Areas<br />
Description<br />
Usage<br />
’area’ is a data frame with three variables.<br />
<strong>The</strong> first variable is a factor defining the polygons.<br />
<strong>The</strong> second and third variables are the xy coordinates of the polygon vertices in the order where<br />
they are found.<br />
area.plot : grey levels areas mapping<br />
poly2area takes an object of class ’polylist’ (spdep package, that contains the older package ’spweights’)<br />
and returns a data frame of type area.<br />
area2poly takes an object of type ’area’ and returns a list of class ’polylist’<br />
area2link takes an object of type ’area’ and returns a proximity matrix which terms are given by the<br />
length of the frontier between two polygons.<br />
area.util.contour,area.util.xy and area.util.class are three utility functions.<br />
area.plot(x, center = NULL, values = NULL, graph = NULL, lwdgraph = 2,<br />
nclasslegend = 8, clegend = 0.75, sub = "", csub = 1,<br />
possub = "topleft", cpoint = 0, label = NULL, clabel = 0, ...)<br />
area2poly(area)<br />
poly2area(polys)<br />
area2link(area)<br />
area.util.contour(area)<br />
area.util.xy(area)<br />
Arguments<br />
x<br />
center<br />
values<br />
graph<br />
lwdgraph<br />
a data frame with three variables<br />
a matrix with the same row number as x and two columns, the coordinates of<br />
polygone centers. If NULL, it is computed with area.util.xy<br />
if not NULL, a vector which values will be mapped to grey levels. <strong>The</strong> values<br />
must be in the same order as the values in unique(x.area[,1])<br />
if not NULL, graph is a neighbouring graph (object of class "neig") between<br />
polygons<br />
a line width to draw the neighbouring graph<br />
nclasslegend if value not NULL, a number of classes for the legend<br />
clegend<br />
sub<br />
csub<br />
if not NULL, a character size for the legend, used with par("cex")*clegend<br />
a string of characters to be inserted as sub-title<br />
a character size for the sub-titles, used with par("cex")*csub
area.plot 21<br />
Value<br />
possub<br />
cpoint<br />
label<br />
clabel<br />
polys<br />
area<br />
a string of characters indicating the sub-titles position ("topleft", "topright",<br />
"bottomleft", "bottomright")<br />
if positive, a character size for drawing the polygons vertices (check up), used<br />
with par("cex")*cpoint<br />
if not NULL, by default the levels of the factor that define the polygons are used<br />
as labels. To change this value, use label. <strong>The</strong>se labels must be in the same order<br />
than unique(x.area[,1])<br />
if not NULL, a character size for the polygon labels,<br />
used with par("cex")*clabel<br />
a list belonging to the ’polylist’ class in the spdep package<br />
a data frame of class ’area’<br />
... further arguments passed to or from other methods<br />
poly2area returns a data frame ’factor,x,y’.<br />
area2poly returns a list of class polylist.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(elec88)<br />
par(mfrow = c(2,2))<br />
area.plot(elec88$area, cpoint = 1)<br />
area.plot(elec88$area, lab = elec88$lab$dep, clab = 0.75)<br />
area.plot(elec88$area, clab = 0.75)<br />
# elec88$neig
22 area.plot<br />
}<br />
data(irishdata)<br />
par(mfrow = c(2,2))<br />
w
arrival 23<br />
# 4<br />
fr.poly
24 as.taxo<br />
Examples<br />
data(arrival)<br />
dotcircle(arrival$hours, pi/2 + pi/12)<br />
as.taxo<br />
Taxonomy<br />
Description<br />
Usage<br />
<strong>The</strong> function as.taxo creates an object of class taxo that is a sub-class of data.frame. Each<br />
column of the data frame must be a factor corresponding to a level j of the taxonomy (genus, family,<br />
. . . ). <strong>The</strong> levels of factor j define some classes that must be completly included in classes of factor<br />
j+1.<br />
A factor with exactly one level is not allowed. A factor with exactly one individual in each level is<br />
not allowed. <strong>The</strong> function dist.taxo compute taxonomic distances.<br />
as.taxo(df)<br />
dist.taxo(taxo)<br />
Arguments<br />
df<br />
taxo<br />
a data frame<br />
a data frame of class taxo<br />
Value<br />
as.taxo returns a data frame of class taxo. dist.taxo returns a numeric of class dist.<br />
Author(s)<br />
Daniel Chessel<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
See Also<br />
taxo2phylog to transform an object of class taxo into an object of class phylog<br />
Examples<br />
data(taxo.eg)<br />
tax
atlas 25<br />
par(mfrow = c(1,1))<br />
all(dist.taxo(tax)==tax.phy$Wdist)<br />
atlas<br />
Small Ecological Dataset<br />
Description<br />
Usage<br />
Format<br />
<strong>Source</strong><br />
atlas is a list containing three kinds of information about 23 regions (<strong>The</strong> French Alps) :<br />
geographical coordinates, meteorology and bird presences.<br />
data(atlas)<br />
This list contains the following objects:<br />
area is a convex hull of 23 geographical regions.<br />
xy are the coordinates of the region centers and altitude (in meters).<br />
names.district is a vector of region names.<br />
meteo is a data frame with 7 variables: min and max temperature in january; min and max temperature<br />
in july; january, july and total rainfalls.<br />
birds is a data frame with 15 variables (species).<br />
alti is a data frame with 3 variables altitude in percentage [0,800], ]800,1500] and ]1500,5000].<br />
Extract from:<br />
Lebreton, Ph. (1977) Les oiseaux nicheurs rhonalpins. Atlas ornithologique Rhone-Alpes. Centre<br />
Ornithologique Rhone-Alpes, Université Lyon 1, 69621 Villeurbanne. Direction de la Protection de<br />
la Nature, Ministère de la Qualité de la Vie. 1–354.<br />
Examples<br />
data(atlas)<br />
op
26 atya<br />
clab = 1)<br />
area.plot(atlas$area, val = dudi.pca(atlas$meteo,scann=FALSE)$li[,1],<br />
ncl = 12, sub = "Principal Component Analysis analysis", csub = 1.5,<br />
cleg = 1)<br />
birds.coa
avijons 27<br />
Examples<br />
## Not run:<br />
data(atya)<br />
if (require(pixmap, quiet = TRUE)) {<br />
atya.digi
28 avijons<br />
References<br />
Thioulouse, J., Chessel, D. and Champely, S. (1995) Multivariate analysis of spatial patterns: a<br />
unified approach to local and global structures. Environmental and Ecological Statistics, 2, 1–14.<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps051.pdf (in French).<br />
Examples<br />
data(avijons)<br />
w1=dudi.coa(avijons$fau,scannf=FALSE)$li<br />
area.plot(avijons$area,center=avijons$xy,val=w1[,1],clab=0.75,sub="CA Axis 1",csub=3)<br />
## Not run:<br />
data(avijons)<br />
if (require(pixmap,quiet=TRUE)) {<br />
pnm.eau
avimedi 29<br />
par(mfcol=c(3,2))<br />
s.value(avijons$xy, jons.ms$li[,1], pixmap = pnm.rou, inclu = FALSE,<br />
grid = FALSE, addax = FALSE, cleg = 0, sub = "F1+ROADS", csub = 3)<br />
s.value(avijons$xy, jons.ms$li[,1], pixmap = pnm.veg, inclu = FALSE,<br />
grid = FALSE, addax = FALSE, cleg = 0, sub = "F1+TREES", csub = 3)<br />
s.value(avijons$xy, jons.ms$li[,1], pixmap = pnm.eau, inclu = FALSE,<br />
grid = FALSE, addax = FALSE, cleg = 0, sub = "F1+WATER", csub = 3)<br />
s.value(avijons$xy, jons.ms$li[,2], pixmap = pnm.rou, inclu = FALSE,<br />
grid = FALSE, addax = FALSE, cleg = 0, sub = "F2+ROADS", csub = 3)<br />
s.value(avijons$xy, jons.ms$li[,2], pixmap = pnm.veg, inclu = FALSE,<br />
grid = FALSE, addax = FALSE, cleg = 0, sub = "F2+TREES", csub = 3)<br />
s.value(avijons$xy, jons.ms$li[,2], pixmap = pnm.eau, inclu = FALSE,<br />
grid = FALSE, addax = FALSE, cleg = 0, sub = "F2+WATER", csub = 3)<br />
par(mfrow=c(1,1))<br />
}## End(Not run)<br />
avimedi<br />
Fauna Table for Constrained Ordinations<br />
Description<br />
avimedi is a list containing the information about 302 sites :<br />
frequencies of 51 bird species ; two factors (habitats and Mediterranean origin).<br />
Usage<br />
data(avimedi)<br />
Format<br />
This list contains the following objects:<br />
fau is a data frame 302 sites - 51 bird species.<br />
plan is a data frame 302 sites - 2 factors : reg with two levels Provence (Pr, South of France) and<br />
Corsica (Co) ; str with six levels describing the vegetation from a very low matorral (1) up<br />
to a mature forest of holm oaks (6).<br />
nomesp is a vector 51 latin names.<br />
<strong>Source</strong><br />
Blondel, J., Chessel, D., & Frochot, B. (1988) Bird species impoverishment, niche expansion, and<br />
density inflation in mediterranean island habitats. Ecology, 69, 1899–1917.
30 aviurba<br />
Examples<br />
## Not run:<br />
data(avimedi)<br />
par(mfrow = c(2,2))<br />
coa1
acteria 31<br />
Details<br />
aviurba$mil contains for each site, 11 habitat attributes describing the degree of urbanization.<br />
<strong>The</strong> presence or absence of farms or villages, small buildings, high buildings, industry, fields, grassland,<br />
scrubby areas, deciduous woods, coniferous woods, noisy area are noticed. At least, the vegetation<br />
cover (variable 11) is a factor with 8 levels from a minimum cover (R5) up to a maximum<br />
(R100).<br />
aviurba$traits contains four factors : feeding habit (insectivor, granivore, omnivore), feeding<br />
stratum (ground, aerial, foliage and scrub), breeding stratum (ground, building, scrub, foliage) and<br />
migration strategy (resident, migrant).<br />
<strong>Source</strong><br />
Dolédec, S., Chessel, D., Ter Braak,C. J. F. and Champely S. (1996) Matching species traits to environmental<br />
variables: a new three-table ordination method. Environmental and Ecological Statistics,<br />
3, 143–166.<br />
Examples<br />
data(aviurba)<br />
a1
32 banque<br />
<strong>Source</strong><br />
Data prepared by J. Lobry 〈lobry@biomserv.univ-lyon1.fr〉 starting from:<br />
http://www.tigr.org/tdb/mdb/mdbcomplete.html<br />
Examples<br />
data(bacteria)<br />
names(bacteria$espcodon)<br />
names(bacteria$espaa)<br />
names(bacteria$espbase)<br />
sum(bacteria$espcodon) # 22,619,749 codons<br />
scatter.coa(dudi.coa(bacteria$espcodon, scann = FALSE),<br />
posi = "bottom")<br />
banque<br />
Table of Factors<br />
Description<br />
Usage<br />
Format<br />
banque gives the results of a bank survey onto 810 customers.<br />
data(banque)<br />
This data frame contains the following columns:<br />
csp : "Socio-professional categories" a factor with levels agric Farmers artis Craftsmen,<br />
Shopkeepers, Company directors cadsu Executives and higher intellectual professions inter<br />
Intermediate professions emplo Other white-collar workers ouvri Manual workers retra<br />
Pensionners inact Non working population etudi Students<br />
duree : "Time relations with the customer" a factor with levels dm2 = 12 years<br />
oppo : "Stopped a check ?" a factor with levels non no oui yes<br />
age : "Customer’s age" a factor with levels ai25 [18 years, 25 years[ ai35 [25 years, 35 years[<br />
ai45 [35 years, 45 years[ ai55 [45 years, 55 years[ ai75 [55 years, 75 years[<br />
sexe : "Customer’s gender" a factor with levels hom Male fem Female<br />
interdit : "No checkbook allowed" a factor with levels non no oui yes<br />
cableue : "Possess a bank card ?" a factor with levels non no oui yes<br />
assurvi : "Contrat of life insurance ?" a factor with levels non no\ oui yes<br />
soldevu : "Balance of the current accounts" a factor with levels p4 credit balance > 20000 p3 credit<br />
balance 12000-20000 p2 credit balance 4000-120000 p1 credit balance >0-4000 n1 debit<br />
balance 0-4000 n2 debit balance >4000
aran95 33<br />
eparlog : "Savings and loan association account amount" a factor with levels for > 20000 fai >0<br />
and 20000 fai >0 and 0 and 20000<br />
versesp : "Check deposits" a factor with levels oui yes non no<br />
retresp : "Cash withdrawals" a factor with levels fai < 2000 moy 2000-5000 for > 5000<br />
remiche : "Endorsed checks amount" a factor with levels for >10000 moy 10000-5000 fai 1-5000<br />
nul none<br />
preltre : "Treasury Department tax deductions" a factor with levels nul none fai 1000<br />
prelfin : "Financial institution deductions" a factor with levels nul none fai 1000<br />
viredeb : "Debit transfer amount" a factor with levels nul none fai 5000<br />
virecre : "Credit transfer amount" a factor with levels for >10000 moy 10000-5000 fai 100000<br />
<strong>Source</strong><br />
anonymous<br />
Examples<br />
data(banque)<br />
banque.acm
34 baran95<br />
Format<br />
<strong>Source</strong><br />
This list contains the following objects:<br />
fau is a data frame 95 seinings and 33 fish species.<br />
plan is a data frame 2 factors : date and site. <strong>The</strong> date has 6 levels (april 1993, june 1993,<br />
august 1993, october 1993, december 1993 and february 1994) and the sites are defined by<br />
4 distances to the Atlantic Ocean (km03, km17, km33 and km46).<br />
species.names is a vector of species latin names.<br />
Baran, E. (1995) Dynamique spatio-temporelle des peuplements de Poissons estuariens en Guinée<br />
(Afrique de l’Ouest). Thèse de Doctorat, Université de Bretagne Occidentale. Data collected by net<br />
fishing sampling in the Fatala river estuary.<br />
References<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps027.pdf (in French).<br />
Examples<br />
data(baran95)<br />
w
etween 35<br />
par(mfrow = c(1,1))<br />
between<br />
Between-Class Analysis<br />
Description<br />
Usage<br />
Performs a particular case of a Principal Component Analysis with respect to Instrumental Variables,<br />
in which there is only one instrumental variable, and it is a factor.<br />
between(dudi, fac, scannf = TRUE, nf = 2)<br />
## S3 method for class 'between':<br />
plot(x, xax = 1, yax = 2, ...)<br />
## S3 method for class 'between':<br />
print(x, ...)<br />
Arguments<br />
dudi<br />
fac<br />
scannf<br />
nf<br />
x<br />
Value<br />
xax, yax<br />
a duality diagram, object of class dudi from one of the functions dudi.coa,<br />
dudi.pca, ...<br />
a factor partitioning the rows of dudi$tab in classes<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, a numeric value indicating the number of kept axes<br />
an object of class ’between’<br />
the numbers of the x-axis and the y-axis<br />
... further arguments passed to or from other methods<br />
Returns a list of subclass ’between’ of class ’dudi’ (see dudi)<br />
tab<br />
cw<br />
lw<br />
eig<br />
rank<br />
nf<br />
c1<br />
l1<br />
co<br />
li<br />
a data frame class-variables, array of variables means in each class<br />
a numeric vector of the column weigths<br />
a numeric vector of the group weigths<br />
a numeric vector with all the eigenvalues<br />
an integer<br />
an integer value indicating the number of kept axes<br />
a data frame with the column normed scores<br />
a data frame with the class normed scores<br />
a data frame with the column coordinates<br />
a data frame with the class coordinates
36 bf88<br />
call<br />
ratio<br />
ls<br />
as<br />
the origin<br />
the bewteen-class inertia percentage<br />
a data frame with the row coordinates<br />
a data frame containing the projection of inertia axes onto between axes<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Dolédec, S. and Chessel, D. (1987) Rythmes saisonniers et composantes stationnelles en milieu<br />
aquatique I- Description d’un plan d’observations complet par projection de variables. Acta Oecologica,<br />
Oecologia Generalis, 8, 3, 403–426.<br />
Examples<br />
data(meaudret)<br />
par(mfrow = c(2,2))<br />
pca1
icenter.wt 37<br />
Format<br />
<strong>Source</strong><br />
A list of six data frames with 79 rows (bird species) and 4 columns (counties).<br />
<strong>The</strong> 6 arrays (S1 to S6) are the 6 stages of vegetation.<br />
<strong>The</strong> attribut ’nomesp’ of this list is a vector of species French names.<br />
Blondel, J. and Farre, H. (1988) <strong>The</strong> convergent trajectories of bird communities along ecological<br />
successions in european forests. Oecologia (Berlin), 75, 83–93.<br />
Examples<br />
data(bf88)<br />
fou1
38 bsetal97<br />
Examples<br />
w
setal97 39<br />
Format<br />
bsetal97 is a list of 8 components.<br />
species.names is a vector of the names of aquatic insects.<br />
taxo is a data frame containing the taxonomy of species: genus, family and order.<br />
biol is a data frame containing 10 biological traits for a total of 41 modalities.<br />
biol.blo is a vector of the numbers of items for each biological trait.<br />
biol.blo.names is a vector of the names of the biological traits.<br />
ecol is a data frame with 7 ecological traits for a total of 34 modalities.<br />
ecol.blo is a vector of the numbers of items for each ecological trait.<br />
ecol.blo.names is a vector of the names of the ecological traits.<br />
Details<br />
<strong>The</strong> 10 variables of the data frame bsetal97$biol are called in bsetal97$biol.blo.names<br />
and the number of modalities per variable given in bsetal97$biol.blo. <strong>The</strong> variables are:<br />
female size - the body length from the front of the head to the end of the abdomen (7 length modalities),<br />
egg length - the egg size (6 modalities), egg number - count of eggs actually oviposited,<br />
generations per year (3 modalities: ≤ 1, 2, > 2), oviposition period - the length of time during<br />
which oviposition occurred (3 modalities: ≤ 2 months, between 2 and 5 months, > 5 months), incubation<br />
time - the time between oviposition and hatching of the larvae (3 modalities: ≤ 4 weeks,<br />
between 4 and 12 weeks, > 12 weeks), egg shape (1-spherical, 2-oval, 3-cylindrical), egg attachment<br />
- physiological feature of the egg and of the female (4 modalities), clutch structure (1-single<br />
eggs, 2-grouped eggs, 3-egg masses), clutch number (3 modalities : 1, 2, > 2).<br />
<strong>The</strong> 7 variables of the data frame bsetal97$ecol are called in bsetal97$ecol.blo.names<br />
and the number of modalities per variable given in bsetal97$ecol.blo. <strong>The</strong> variables are:<br />
oviposition site - position relative to the water (7 modalities), substratum type for eggs - the substratum<br />
to which the eggs are definitely attached (6 modalities), egg deposition - the position of<br />
the eggs during the oviposition process (4 modalities), gross habitat - the general habitat use of the<br />
species such as temporary waters or estuaries (8 modalities), saturation variance - the exposure of<br />
eggs to the risk of dessication (2 modalities), time of day (1-morning, 2-day, 3-evening, 4-night),<br />
season - time of the year (1-Spring, 2-Summer, 3-Automn).<br />
<strong>Source</strong><br />
Statzner, B., Hoppenhaus, K., Arens, M.-F. and Richoux, P. (1997) Reproductive traits, habitat use<br />
and templet theory: a synthesis of world-wide data on aquatic insects. Freshwater Biology, 38,<br />
109–135.<br />
References<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps029.pdf (in French).
40 buech<br />
Examples<br />
data(bsetal97)<br />
X
utterfly 41<br />
Examples<br />
data(buech)<br />
par(mfrow = c(1,2))<br />
s.label(buech$xy, contour = buech$contour, neig = buech$neig)<br />
s.value (buech$xy, buech$tab2$Suspens-buech$tab1$Suspens,<br />
contour = buech$contour, neig = buech$neig, csi = 3)<br />
par(mfrow = c(1,1))<br />
butterfly<br />
Genetics-Ecology-Environment Triple<br />
Description<br />
Usage<br />
Format<br />
<strong>Source</strong><br />
This data set contains environmental and genetics informations about 16 Euphydryas editha butterfly<br />
colonies studied in California and Oregon.<br />
data(butterfly)<br />
butterfly is a list with 4 components.<br />
xy is a data frame with the two coordinates of the 16 Euphydryas editha butterfly colonies.<br />
envir is a environmental data frame of 16 sites - 4 variables.<br />
genet is a genetics data frame of 16 sites - 6 allele frequencies.<br />
contour is a data frame for background map (California map).<br />
McKechnie, S.W., Ehrlich, P.R. and White, R.R. (1975) Population genetics of Euphydryas butterflies.<br />
I. Genetic variation and the neutrality hypothesis. Genetics, 81, 571–594.<br />
References<br />
Manly, B.F. (1994) Multivariate Statistical Methods. A primer. Second edition. Chapman & Hall,<br />
London. 1–215.<br />
Examples<br />
data(butterfly)<br />
par(mfrow = c(2,2))<br />
s.label(butterfly$xy, contour = butterfly$contour, inc = FALSE)<br />
table.dist(dist(butterfly$xy), labels = row.names(butterfly$xy)) # depends of mva<br />
s.value(butterfly$xy, dudi.pca(butterfly$envir, scan = FALSE)$li[,1],<br />
contour = butterfly$contour, inc = FALSE, csi = 3)<br />
plot(mantel.randtest(dist(butterfly$xy), dist(butterfly$gen), 99),<br />
main = "genetic/spatial")<br />
par(mfrow = c(1,1))
42 cailliez<br />
cailliez<br />
Transformation to make Euclidean a distance matrix<br />
Description<br />
Usage<br />
This function computes the smallest positive constant that makes Euclidean a distance matrix and<br />
applies it.<br />
cailliez(distmat, print = FALSE)<br />
Arguments<br />
distmat<br />
print<br />
an object of class dist<br />
if TRUE, prints the eigenvalues of the matrix<br />
Value<br />
an object of class dist containing a Euclidean distance matrix.<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Cailliez, F. (1983) <strong>The</strong> analytical solution of the additive constant problem. Psychometrika, 48,<br />
305–310.<br />
Legendre, P. and Anderson, M.J. (1999) Distance-based redundancy analysis: testing multispecies<br />
responses in multifactorial ecological experiments. Ecological Monographs, 69, 1–24.<br />
Legendre, P., and Legendre, L. (1998) Numerical ecology, 2nd English edition edition. Elsevier<br />
Science BV, Amsterdam.<br />
From the DistPCoa program of P. Legendre et M.J. Anderson<br />
http://www.fas.umontreal.ca/BIOL/Casgrain/en/labo/distpcoa.html<br />
Examples<br />
data(capitales)<br />
d0
capitales 43<br />
is.euclid(d1) # TRUE<br />
plot(d0, d1)<br />
abline(lm(unclass(d1)~unclass(d0)))<br />
print(coefficients(lm(unclass(d1)~unclass(d0))), dig = 8) # d1 = d + Cte<br />
is.euclid(d0 + 2428) # FALSE<br />
is.euclid(d0 + 2430) # TRUE the smallest constant<br />
capitales<br />
Road Distances<br />
Description<br />
Usage<br />
Format<br />
<strong>Source</strong><br />
This data set gives the road distances between 15 European capitals and their coordinates.<br />
data(capitales)<br />
This list contains the following objects:<br />
df is a data frame containing the road distances between 15 European capitals.<br />
xy is a data frame containing the coordinates of capitals.<br />
area is a data frame containing three variables, designed to be used in area.plot function.<br />
logo is a list of pixmap objects, each one symbolizing a capital<br />
http://www.euro.gouv.fr/jeunes/eurocollege/tableaucarte.htm<br />
Examples<br />
if (require(pixmap, quiet = TRUE)) {<br />
data(capitales)<br />
names(capitales$df)<br />
# [1] "Madrid" "Paris" "Londres" "Dublin" "Rome"<br />
# [6] "Bruxelles" "Amsterdam" "Berlin" "Copenhague" "Stokholm"<br />
#[11] "Luxembourg" "Helsinki" "Vienne" "Athenes" "Lisbonne"<br />
}<br />
index
44 carni70<br />
carni19<br />
Phylogeny and quantative trait of carnivora<br />
Description<br />
This data set describes the phylogeny of carnivora as reported by Diniz-Filho et al. (1998). It also<br />
gives the body mass of these 19 species.<br />
Usage<br />
data(carni19)<br />
Format<br />
carni19 is a list containing the 2 following objects :<br />
tre is a character string giving the phylogenetic tree in Newick format.<br />
bm is a numeric vector which values correspond to the body mass of the 19 species (log scale).<br />
<strong>Source</strong><br />
Diniz-Filho, J. A. F., de Sant’Ana, C.E.R. and Bini, L.M. (1998) An eigenvector method for estimating<br />
phylogenetic inertia. Evolution, 52, 1247–1262.<br />
Examples<br />
data(carni19)<br />
carni19.phy
carniherbi49 45<br />
Format<br />
<strong>Source</strong><br />
carni70 is a list containing the 2 following objects:<br />
tre is a character string giving the phylogenetic tree in Newick format. Branch lengths are expressed<br />
as divergence times (millions of years)<br />
tab is a data frame with 70 species and two traits: size (body size (kg)) ; range (geographic range<br />
size (km)).<br />
Diniz-Filho, J. A. F., and N. M. Tôrres. (2002) Phylogenetic comparative methods and the geographic<br />
range size-body size relationship in new world terrestrial carnivora. Evolutionary Ecology,<br />
16, 351–367.<br />
Examples<br />
## Not run:<br />
data(carni70)<br />
carni70.phy
46 casitas<br />
Format<br />
carniherbi49 is a list containing the 5 following objects :<br />
taxo is a data frame with 49 species and 2 columns : ’fam’, a factor family with 14 levels and ’ord’,<br />
a factor order with 3 levels.<br />
tre1 is a character string giving the phylogenetic tree in Newick format as reported by Garland et<br />
al. (1993).<br />
tre2 is a character string giving the phylogenetic tree in Newick format as reported by Garland and<br />
Janis (1993).<br />
tab1 is a data frame with 49 species and 2 traits: ’bodymass’ (body mass (kg)) and ’homerange’<br />
(home range (km)).<br />
tab2 is a data frame with 49 species and 5 traits: ’clade’ (dietary with two levels Carnivore<br />
and Herbivore), ’runningspeed’ (maximal sprint running speed (km/h)), ’bodymass’ (body<br />
mass (kg)), ’hindlength’ (hind limb length (cm)) and ’mtfratio’ (metatarsal/femur ratio).<br />
<strong>Source</strong><br />
Garland, T., Dickerman, A. W., Janis, C. M. and Jones, J. A. (1993) Phylogenetic analysis of covariance<br />
by computer simulation. Systematics Biology, 42, 265–292.<br />
Garland, T. J. and Janis, C.M. (1993) Does metatarsal-femur ratio predict maximal running speed<br />
in cursorial mammals? Journal of Zoology, 229, 133–151.<br />
Examples<br />
## Not run:<br />
data(carniherbi49)<br />
par(mfrow=c(1,3))<br />
plot(newick2phylog(carniherbi49$tre1), clabel.leaves = 0,<br />
f.phylog = 2, sub ="article 1")<br />
plot(newick2phylog(carniherbi49$tre2), clabel.leaves = 0,<br />
f.phylog = 2, sub = "article 2")<br />
taxo
cca 47<br />
Usage<br />
data(casitas)<br />
Format<br />
<strong>The</strong> 74 individuals of casitas belong to 4 groups:<br />
1 24 mice of the sub-species Mus musculus domesticus<br />
2 11 mice of the sub-species Mus musculus castaneus<br />
3 9 mice of the sub-species Mus musculus musculus<br />
4 30 mice from a population of the lake Casitas (California)<br />
<strong>Source</strong><br />
Exemple du logiciel GENETIX. Belkhir k. et al. GENETIX, logiciel sous WindowsTM pour<br />
la génétique des populations. Laboratoire Génome, Populations, Interactions CNRS UMR 5000,<br />
Université de Montpellier II, Montpellier (France).<br />
http://www.univ-montp2.fr/~genetix/genetix/genetix.htm<br />
References<br />
Orth, A., T. Adama, W. Din and F. Bonhomme. (1998) Hybridation naturelle entre deux sous<br />
espèces de souris domestique Mus musculus domesticus et Mus musculus castaneus près de Lake<br />
Casitas (Californie). Genome, 41, 104–110.<br />
Examples<br />
data(casitas)<br />
casitas.pop
48 cca<br />
Arguments<br />
sitspe<br />
sitenv<br />
scannf<br />
nf<br />
a data frame for correspondence analysis, typically a sites x species table<br />
a data frame containing variables, typically a sites x environmental variables<br />
table<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
Value<br />
returns an object of class pcaiv. See pcaiv<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Ter Braak, C. J. F. (1986) Canonical correspondence analysis : a new eigenvector technique for<br />
multivariate direct gradient analysis. Ecology, 67, 1167–1179.<br />
Ter Braak, C. J. F. (1987) <strong>The</strong> analysis of vegetation-environment relationships by canonical correspondence<br />
analysis. Vegetatio, 69, 69–77.<br />
Chessel, D., Lebreton J. D. and Yoccoz N. (1987) Propriétés de l’analyse canonique des correspondances.<br />
Une utilisation en hydrobiologie. Revue de Statistique Appliquée, 35, 55–72.<br />
See Also<br />
cca in the package vegan<br />
Examples<br />
data(rpjdl)<br />
millog
chatcat 49<br />
s.match(iv1$ls, iv1$li, 2, 1, clab = 0.5)<br />
# analysis with fa - l1 - co -cor<br />
# canonical weights giving unit variance combinations<br />
s.arrow(iv1$fa)<br />
# sites position by environmental variables combinations<br />
# position of species by averaging<br />
s.label(iv1$l1, 2, 1, clab = 0, cpoi = 1.5)<br />
s.label(iv1$co, 2, 1, add.plot = TRUE)<br />
s.distri(iv1$l1, rpjdl$fau, 2, 1, cell = 0, csta = 0.33)<br />
s.label(iv1$co, 2, 1, clab = 0.75, add.plot = TRUE)<br />
# coherence between weights and correlations<br />
par(mfrow = c(1,2))<br />
s.corcircle(iv1$cor, 2, 1)<br />
s.arrow(iv1$fa, 2, 1)<br />
par(mfrow = c(1,1))<br />
chatcat<br />
Qualitative Weighted Variables<br />
Description<br />
This data set gives the age, the fecundity and the number of litters for 26 groups of cats.<br />
Usage<br />
data(chatcat)<br />
Format<br />
Details<br />
chatcat is a list of two objects :<br />
tab is a data frame with 3 factors (age, feco, nport).<br />
eff is a vector of numbers.<br />
One row of tab corresponds to one group of cats.<br />
<strong>The</strong> value in eff is the number of cats in this group.<br />
<strong>Source</strong><br />
Pontier, D. (1984) Contribution à la biologie et à la génétique des populations de chats domestiques<br />
(Felis catus). Thèse de 3ème cycle. Université Lyon 1, p. 67.
50 chats<br />
Examples<br />
data(chatcat)<br />
summary(chatcat$tab)<br />
w
chazeb 51<br />
chazeb<br />
Charolais-Zebus<br />
Description<br />
Usage<br />
Format<br />
<strong>Source</strong><br />
This data set gives six different weights of 23 charolais and zebu oxen.<br />
data(chazeb)<br />
chazeb is a list of 2 components.<br />
tab is a data frame with 23 rows and 6 columns.<br />
cla is a factor with two levels "cha" and "zeb".<br />
Tomassone, R., Danzard, M., Daudin, J. J. and Masson J. P. (1988) Discrimination et classement,<br />
Masson, Paris. p. 43<br />
Examples<br />
data(chazeb)<br />
plot(discrimin(dudi.pca(chazeb$tab, scan = FALSE),<br />
chazeb$cla, scan = FALSE))<br />
chevaine<br />
Enzymatic polymorphism in Leuciscus cephalus<br />
Description<br />
This data set contains a list of three components: spatial map, allellic profiles and sample sizes.<br />
Usage<br />
data(chevaine)<br />
Format<br />
This data set is a list of three components:<br />
tab a data frame with 27 populations and 9 allelic frequencies (4 locus)<br />
coo a list containing all the elements to build a spatial map<br />
eff a numeric containing the numbers of fish samples per station
52 clementines<br />
References<br />
Guinand B., Bouvet Y. and Brohon B. (1996) Spatial aspects of genetic differentiation of the European<br />
chub in the Rhone River basin. Journal of Fish Biology, 49, 714–726.<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps054.pdf (in French).<br />
Examples<br />
data(chevaine)<br />
'fun.chevaine'
cnc2003 53<br />
Usage<br />
data(clementines)<br />
Format<br />
A data frame with 15 rows and 20 columns<br />
<strong>Source</strong><br />
Tisné-Agostini, D. (1988) Description par analyse en composantes principales de l’évolution de la<br />
production du clémentinier en association avec 12 types de porte-greffe. Rapport technique, DEA<br />
Analyse et modélisation des systèmes biologiques, Université Lyon 1.<br />
Examples<br />
data(clementines)<br />
op
54 cnc2003<br />
Description<br />
cnc2003 is a data frame with 94 rows (94 departments from continental Metropolitan France)and<br />
12 variables.<br />
Usage<br />
data(cnc2003)<br />
Format<br />
This data frame contains the following variables:<br />
popu is the population department in million inhabitants.<br />
entr is the number of movie theater visitors in million.<br />
rece is the takings from ticket offices.<br />
sean is the number of proposed shows in thousands.<br />
comm is the number of equipped communes in movie theaters (units).<br />
etab is the number of active movie theaters (units).<br />
salle is the number of active screens.<br />
faut is the number of proposed seats.<br />
artes is the number of movie theaters offering "Art and Essay" movies.<br />
multi is the number of active multiplexes.<br />
depart is the name of the department.<br />
reg is the administrative region of the department.<br />
<strong>Source</strong><br />
National Center of Cinematography (CNC), september 2003<br />
http://www.cnc.fr/cncinfo/288/index.html<br />
See Also<br />
This dataset is compatible with elec88 and presid2002<br />
Examples<br />
data(cnc2003)<br />
sco.quant(cnc2003$popu, cnc2003[,2:10], abline = TRUE, csub = 3)
coinertia 55<br />
coinertia<br />
Coinertia Analysis<br />
Description<br />
Usage<br />
<strong>The</strong> coinertia analysis performs a double inertia analysis of two arrays.<br />
coinertia(dudiX, dudiY, scannf = TRUE, nf = 2)<br />
## S3 method for class 'coinertia':<br />
plot (x, xax = 1, yax = 2, ...)<br />
## S3 method for class 'coinertia':<br />
print (x, ...)<br />
## S3 method for class 'coinertia':<br />
summary (object, ...)<br />
Arguments<br />
dudiX a duality diagram providing from one of the functions dudi.coa, dudi.pca, . . .<br />
dudiY a duality diagram providing from one of the functions dudi.coa, dudi.pca, . . .<br />
scannf<br />
nf<br />
Value<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
x, object an object of class ’coinertia’<br />
xax, yax<br />
the numbers of the x-axis and the y-axis<br />
... further arguments passed to or from other methods<br />
Returns a list of class ’coinertia’, sub-class ’dudi’ containing:<br />
call<br />
rank<br />
nf<br />
RV<br />
eig<br />
lw<br />
cw<br />
tab<br />
li<br />
l1<br />
co<br />
call<br />
rank<br />
a numeric value indicating the number of kept axes<br />
a numeric value, the RV coefficient<br />
a numeric vector with all the eigenvalues<br />
a numeric vector with the rows weigths (crossed array)<br />
a numeric vector with the columns weigths (crossed array)<br />
a crossed array (CA)<br />
Y col = CA row: coordinates<br />
Y col = CA row: normed scores<br />
X col = CA column: coordinates
56 coinertia<br />
c1<br />
lX<br />
mX<br />
lY<br />
mY<br />
aX<br />
aY<br />
X col = CA column: normed scores<br />
the row coordinates (X)<br />
the normed row scores (X)<br />
the row coordinates (Y)<br />
the normed row scores (Y)<br />
the axis onto co-inertia axis (X)<br />
the axis onto co-inertia axis (Y)<br />
WARNING<br />
IMPORTANT : dudi1 and dudi2 must have identical row weights.<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Dolédec, S. and Chessel, D. (1994) Co-inertia analysis: an alternative method for studying speciesenvironment<br />
relationships. Freshwater Biology, 31, 277–294.<br />
Dray, S., Chessel, D. and J. Thioulouse (2003) Co-inertia analysis and the linking of the ecological<br />
data tables. Ecology, 84, 11, 3078–3089.<br />
Examples<br />
data(doubs)<br />
dudi1
coleo 57<br />
coleo<br />
Table of Fuzzy Biological Traits<br />
Description<br />
This data set coleo (coleoptera) is a a fuzzy biological traits table.<br />
Usage<br />
data(coleo)<br />
Format<br />
coleo is a list of 5 components.<br />
tab is a data frame with 110 rows (species) and 32 columns (categories).<br />
species.names is a vector of species names.<br />
moda.names is a vector of fuzzy variables names.<br />
families is a factor species family.<br />
col.blocks is a vector containing the number of categories of each trait.<br />
<strong>Source</strong><br />
Bournaud, M., Richoux, P. and Usseglio-Polatera, P. (1992) An approach to the synthesis of qualitative<br />
ecological information from aquatic coleoptera communities. Regulated rivers: Research and<br />
Management, 7, 165–180.<br />
Examples<br />
data(coleo)<br />
op
58 corkdist<br />
corkdist<br />
Tests of randomization between distances applied to ’kdist’ objetcs<br />
Description<br />
Usage<br />
<strong>The</strong> mantelkdist and RVkdist functions apply to blocks of distance matrices the mantel.rtest and<br />
RV.rtest functions.<br />
mantelkdist (kd, nrepet = 999)<br />
RVkdist (kd, nrepet = 999)<br />
## S3 method for class 'corkdist':<br />
plot(x, whichinrow = NULL, whichincol = NULL,<br />
gap = 4, nclass = 10, coeff = 1,...)<br />
Arguments<br />
kd<br />
nrepet<br />
x<br />
whichinrow<br />
whichincol<br />
gap<br />
Details<br />
Value<br />
nclass<br />
coeff<br />
a list of class kdist<br />
the number of permutations<br />
an objet of class corkdist, coming from RVkdist or mantelkdist<br />
a vector of integers to select the graphs in rows (if NULL all the graphs are<br />
computed)<br />
a vector of integers to select the graphs in columns (if NULL all the graphs are<br />
computed)<br />
an integer to determinate the space between two graphs<br />
a number of intervals for the histogram<br />
an integer to fit the magnitude of the graph<br />
... further arguments passed to or from other methods<br />
<strong>The</strong> corkdist class has some generic functions print, plot and summary. <strong>The</strong> plot shows<br />
bivariate scatterplots between semi-matrices of distances or histograms of simulated values with an<br />
error position.<br />
a list of class corkdist containing for each pair of distances an object of class randtest (permutation<br />
tests).<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉
corvus 59<br />
Examples<br />
data(friday87)<br />
fri.w
60 deug<br />
Examples<br />
data(corvus)<br />
plot(corvus[,1:2])<br />
s.class(corvus[,1:2], corvus[,4]:corvus[,3], add.p = TRUE)<br />
deug<br />
Exam marks for some students<br />
Description<br />
This data set gives the exam results of 104 students in the second year of a French University onto<br />
9 subjects.<br />
Usage<br />
data(deug)<br />
Format<br />
deug is a list of three components.<br />
tab is a data frame with 104 students and 9 subjects : Algebra, Analysis, Proba, Informatic, Economy,<br />
Option1, Option2, English, Sport.<br />
result is a factor of 104 components giving the final exam levels (A+, A, B, B-, C-, D).<br />
cent is a vector of required marks by subject to get exactly 10/20 with a coefficient.<br />
<strong>Source</strong><br />
University of Lyon 1<br />
Examples<br />
data(deug)<br />
# decentred PCA<br />
pca1
disc 61<br />
disc<br />
Rao’s dissimilarity coefficient<br />
Description<br />
Calculates the root square of Rao’s dissimilarity coefficient between samples.<br />
Usage<br />
disc(samples, dis = NULL, structures = NULL)<br />
Arguments<br />
samples<br />
dis<br />
structures<br />
a data frame with elements as rows, samples as columns, and abundance, presenceabsence<br />
or frequencies as entries<br />
an object of class dist containing distances or dissimilarities among elements.<br />
If dis is NULL, equidistances are used.<br />
a data frame containing, in the jth row and the kth column, the name of the group<br />
of level k to which the jth population belongs.<br />
Value<br />
Returns a list of objects of class dist<br />
Author(s)<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉<br />
References<br />
Rao, C.R. (1982) Diversity and dissimilarity coefficients: a unified approach. <strong>The</strong>oretical Population<br />
Biology, 21, 24–43.<br />
Examples<br />
data(humDNAm)<br />
humDNA.dist
62 discrimin<br />
discrimin<br />
Linear Discriminant Analysis (descriptive statistic)<br />
Description<br />
Usage<br />
performs a linear discriminant analysis.<br />
discrimin(dudi, fac, scannf = TRUE, nf = 2)<br />
## S3 method for class 'discrimin':<br />
plot(x, xax = 1, yax = 2, ...)<br />
## S3 method for class 'discrimin':<br />
print(x, ...)<br />
Arguments<br />
dudi<br />
fac<br />
scannf<br />
nf<br />
x<br />
Value<br />
xax<br />
yax<br />
a duality diagram, object of class dudi<br />
a factor defining the classes of discriminant analysis<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
an object of class ’discrimin’<br />
the column number of the x-axis<br />
the column number of the y-axis<br />
... further arguments passed to or from other methods<br />
returns a list of class ’discrimin’ containing :<br />
nf<br />
eig<br />
fa<br />
li<br />
va<br />
cp<br />
gc<br />
a numeric value indicating the number of kept axes<br />
a numeric vector with all the eigenvalues<br />
a matrix with the loadings: the canonical weights<br />
a data frame which gives the canonical scores<br />
a matrix which gives the cosines between the variables and the canonical scores<br />
a matrix which gives the cosines between the components and the canonical<br />
scores<br />
a data frame which gives the class scores<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉
discrimin.coa 63<br />
See Also<br />
lda in package MASS<br />
Examples<br />
data(chazeb)<br />
dis1
64 dist.binary<br />
References<br />
Perriere, G.,Lobry, J. R. and Thioulouse J. (1996) Correspondence discriminant analysis: a multivariate<br />
method for comparing classes of protein and nucleic acid sequences. CABIOS, 12, 519–524.<br />
Perriere, G. and Thioulouse, J. (2003) Use of Correspondence Discriminant Analysis to predict the<br />
subcellular location of bacterial proteins. Computer Methods and Programs in Biomedicine, 70, 2,<br />
99–105.<br />
Examples<br />
data(perthi02)<br />
plot(discrimin.coa(perthi02$tab, perthi02$cla, scan = FALSE))<br />
dist.binary<br />
Computation of Distance Matrices for Binary Data<br />
Description<br />
computes for binary data some distance matrice.<br />
Usage<br />
dist.binary(df, method = NULL, diag = FALSE, upper = FALSE)<br />
Arguments<br />
df<br />
method<br />
diag<br />
upper<br />
a data frame with positive or zero values. Used with as.matrix(1 * (df<br />
> 0))<br />
an integer between 1 and 10 . If NULL the choice is made with a console<br />
message. See details<br />
a logical value indicating whether the diagonal of the distance matrix should be<br />
printed by ‘print.dist’<br />
a logical value indicating whether the upper triangle of the distance matrix<br />
should be printed by ‘print.dist’<br />
Details<br />
Let be the contingency table of binary data such as n 11 = a, n 10 = b, n 01 = c and n 00 = d. All<br />
these distances are of type d = √ 1 − s with s a similarity coefficient.<br />
1 = Jaccard index (1901) S3 coefficient of Gower & Legendre s 1 = a<br />
a+b+c<br />
2 = Sockal & Michener index (1958) S4 coefficient of Gower & Legendre s 2 = a+d<br />
a+b+c+d<br />
3 = Sockal & Sneath(1963) S5 coefficient of Gower & Legendre s 3 =<br />
a<br />
a+2(b+c)<br />
4 = Rogers & Tanimoto (1960) S6 coefficient of Gower & Legendre s 4 =<br />
a+d<br />
(a+2(b+c)+d)
dist.dudi 65<br />
5 = Czekanowski (1913) or Sorensen (1948) S7 coefficient of Gower & Legendre s 5 = 2a<br />
2a+b+c<br />
6 = S9 index of Gower & Legendre (1986) s 6 = a−(b+c)+d<br />
a+b+c+d<br />
a<br />
7 = Ochiai (1957) S12 coefficient of Gower & Legendre s 7 = √<br />
(a+b)(a+c)<br />
ad<br />
8 = Sockal & Sneath (1963) S13 coefficient of Gower & Legendre s 8 = √<br />
(a+b)(a+c)(d+b)(d+c)<br />
ad−bc<br />
9 = Phi of Pearson S14 coefficient of Gower & Legendre s 9 = √<br />
(a+b)(a+c)(b+d)(d+c)<br />
10 = S2 coefficient of Gower & Legendre s 1 =<br />
a<br />
a+b+c+d<br />
Value<br />
returns a distance matrix of class dist between the rows of the data frame<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Gower, J.C. and Legendre, P. (1986) Metric and Euclidean properties of dissimilarity coefficients.<br />
Journal of Classification, 3, 5–48.<br />
Examples<br />
data(aviurba)<br />
for (i in 1:10) {<br />
d
66 dist.genet<br />
Value<br />
an object of class dist<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
Examples<br />
data (meaudret)<br />
pca1
dist.genet 67<br />
Let P the table of general term p k ij<br />
p + ij = ∑ m(j)<br />
k=1 pk ij = 1, p+ i+ = ∑ ν<br />
j=1 p+ ij = ν, p+ ++ = ∑ ν<br />
j=1 p+ i+ = tν<br />
<strong>The</strong> option method computes the distance matrices between populations using the frequencies p k ij .<br />
Value<br />
1. Nei’s distance:<br />
D 1 (a, b) = − ln(<br />
√ ∑ν<br />
k=1<br />
∑ ν<br />
∑ m(k)<br />
k=1 j=1 pk aj pk bj<br />
∑ )<br />
m(k)<br />
j=1 (pk bj )2<br />
∑ m(k)<br />
j=1 (pk aj )2 √ ∑ν<br />
k=1<br />
2. Angular distance √ or Edwards’ distance:<br />
D 2 (a, b) =<br />
1 − 1 ν<br />
∑ ν<br />
k=1<br />
∑ m(k)<br />
j=1<br />
√<br />
p k aj pk bj<br />
3. Coancestrality coefficient or Reynolds’ distance:<br />
D 3 (a, b) =<br />
√ ∑ν ∑ m(k)<br />
∑ k=1 j=1 (pk aj −pk bj )2<br />
ν<br />
2 (1−∑ m(k)<br />
k=1 j=1 pk aj pk bj )<br />
4. Classical Euclidean distance or Rogers’ distance:<br />
D 4 (a, b) = 1 ∑ ν ∑ m(k)<br />
ν k=1 j=1 (pk aj − pk bj )2<br />
√<br />
1<br />
2<br />
5. Absolute genetics distance or Provesti ’s distance:<br />
D 5 (a, b) = 1 ∑ ν ∑ m(k)<br />
2ν k=1 j=1 |pk aj − pk bj |<br />
returns a distance matrix of class dist between the rows of the data frame<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
To complete informations about distances:<br />
Distance 1:<br />
Nei, M. (1972) Genetic distances between populations. American Naturalist, 106, 283–292.<br />
Nei M. (1978) Estimation of average heterozygosity and genetic distance from a small number of<br />
individuals. Genetics, 23, 341–369.<br />
Avise, J. C. (1994) Molecular markers, natural history and evolution. Chapman & Hall, London.<br />
Distance 2:<br />
Edwards, A.W.F. (1971) Distance between populations on the basis of gene frequencies. Biometrics,<br />
27, 873–881.<br />
Cavalli-Sforza L.L. and Edwards A.W.F. (1967) Phylogenetic analysis: models and estimation procedures.<br />
Evolution, 32, 550–570.
68 dist.neig<br />
Hartl, D.L. and Clark, A.G. (1989) Principles of population genetics. Sinauer Associates, Sunderland,<br />
Massachussetts (p. 303).<br />
Distance 3:<br />
Reynolds, J. B., B. S. Weir, and C. C. Cockerham. (1983) Estimation of the coancestry coefficient:<br />
basis for a short-term genetic distance. Genetics, 105, 767–779.<br />
Distance 4:<br />
Rogers, J.S. (1972) Measures of genetic similarity and genetic distances. Studies in Genetics, Univ.<br />
Texas Publ., 7213, 145–153.<br />
Avise, J. C. (1994) Molecular markers, natural history and evolution. Chapman & Hall, London.<br />
Distance 5:<br />
Prevosti A. (1974) La distancia genética entre poblaciones. Miscellanea Alcobé, 68, 109–118.<br />
Prevosti A., Ocaña J. and Alonso G. (1975) Distances between populations of Drosophila subobscura,<br />
based on chromosome arrangements frequencies. <strong>The</strong>oretical and Applied Genetics, 45,<br />
231–241.<br />
To find some useful explanations:<br />
Sanchez-Mazas A. (2003) Cours de Génétique Moléculaire des Populations. Cours VIII Distances<br />
génétiques - Représentation des populations.<br />
http://anthro.unige.ch/GMDP/Alicia/GMDP_dist.htm<br />
Examples<br />
data(casitas)<br />
casi.genet
dist.prop 69<br />
Value<br />
returns a distance matrix, object of class dist<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
Examples<br />
data(elec88)<br />
d0
70 dist.quant<br />
4 = Nei 1972 (one locus) d 4 = ln<br />
∑ K<br />
√ i=1 piqi<br />
∑K<br />
√<br />
∑K<br />
i=1 p2 i i=1 q2 i<br />
5 = Edwards 1971 (one locus) d 5 =<br />
√<br />
1 − ∑ K<br />
i=1<br />
√<br />
p1 q i<br />
Value<br />
returns a distance matrix, object of class dist<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Edwards, A. W. F. (1971) Distance between populations on the basis of gene frequencies. Biometrics,<br />
27, 873–881.<br />
Manly, B. F. (1994) Multivariate Statistical Methods. A primer., Second edition. Chapman & Hall,<br />
London.<br />
Nei, M. (1972) Genetic distances between populations. <strong>The</strong> American Naturalist, 106, 283–292.<br />
Examples<br />
data(microsatt)<br />
w
dist.quant 71<br />
Arguments<br />
df<br />
method<br />
diag<br />
upper<br />
tol<br />
a data frame containing only quantitative variables<br />
an integer between 1 and 3. If NULL the choice is made with a console message.<br />
See details<br />
a logical value indicating whether the diagonal of the distance matrix should be<br />
printed by ‘print.dist’<br />
a logical value indicating whether the upper triangle of the distance matrix<br />
should be printed by ‘print.dist’<br />
used in case 3 of method as a tolerance threshold for null eigenvalues<br />
Details<br />
All the distances are of type d = ‖x − y‖ A = √ (x − y) t A(x − y)<br />
1 = Canonical A = Identity<br />
2 = Joreskog A =<br />
1<br />
diag(cov)<br />
3 = Mahalanobis A = inv(cov)<br />
Value<br />
an object of class dist<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
Examples<br />
data(ecomor)<br />
par(mfrow = c(2,2))<br />
scatter(dudi.pco(dist.quant(ecomor$morpho,3), scan = FALSE))<br />
scatter(dudi.pco(dist.quant(ecomor$morpho,2), scan = FALSE))<br />
scatter(dudi.pco(dist(scalewt(ecomor$morpho)), scan = FALSE))<br />
scatter(dudi.pco(dist.quant(ecomor$morpho,1), scan = FALSE))<br />
par(mfrow = c(1,1))
72 divc<br />
divc<br />
Rao’s diversity coefficient also called quadratic entropy<br />
Description<br />
Calculates Rao’s diversity coefficient within samples.<br />
Usage<br />
divc(df, dis, scale)<br />
Arguments<br />
df<br />
dis<br />
scale<br />
a data frame with elements as rows, samples as columns, and abundance, presenceabsence<br />
or frequencies as entries<br />
an object of class dist containing distances or dissimilarities among elements.<br />
If dis is NULL, Gini-Simpson index is performed.<br />
a logical value indicating whether or not the diversity coefficient should be<br />
scaled by its maximal value over all frequency distributions.<br />
Value<br />
Returns a data frame with samples as rows and the diversity coefficient within samples as columns<br />
Author(s)<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉<br />
References<br />
Rao, C.R. (1982) Diversity and dissimilarity coefficients: a unified approach. <strong>The</strong>oretical Population<br />
Biology, 21, 24–43.<br />
Gini, C. (1912) Variabilitá e mutabilitá. Universite di Cagliari III, Parte II.<br />
Simpson, E.H. (1949) Measurement of diversity. Nature, 163, 688.<br />
Champely, S. and Chessel, D. (2002) Measuring biological diversity using Euclidean metrics. Environmental<br />
and Ecological Statistics, 9, 167–177.<br />
Examples<br />
data(ecomor)<br />
dtaxo
divcmax 73<br />
divcmax<br />
Maximal value of Rao’s diversity coefficient also called quadratic entropy<br />
Description<br />
Usage<br />
For a given dissimilarity matrix, this function calculates the maximal value of Rao’s diversity coefficient<br />
over all frequency distribution. It uses an optimization technique based on Rosen’s projection<br />
gradient algorithm and is verified using the Kuhn-Tucker conditions.<br />
divcmax(dis, epsilon, comment)<br />
Arguments<br />
dis<br />
epsilon<br />
comment<br />
an object of class dist containing distances or dissimilarities among elements.<br />
a tolerance threshold : a frequency is non null if it is higher than epsilon.<br />
a logical value indicating whether or not comments on the optimization technique<br />
should be printed.<br />
Value<br />
Returns a list<br />
value<br />
vectors<br />
the maximal value of Rao’s diversity coefficient.<br />
a data frame containing four frequency distributions : sim is a simple distribution<br />
which is equal to<br />
D1<br />
1 t D1 , pro is equal to z<br />
1 t z1<br />
, where z is the nonnegative<br />
eigenvector of the matrix containing the squared dissimilarities among the elements,<br />
met is equal to z 2 , num is a frequency vector maximizing Rao’s diversity<br />
coefficient.<br />
Author(s)<br />
Stéphane Champely 〈Stephane.Champely@univ-lyon1.fr〉<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉<br />
References<br />
Rao, C.R. (1982) Diversity and dissimilarity coefficients: a unified approach. <strong>The</strong>oretical Population<br />
Biology, 21, 24–43.<br />
Gini, C. (1912) Variabilitá e mutabilitá. Universite di Cagliari III, Parte II.<br />
Simpson, E.H. (1949) Measurement of diversity. Nature, 163, 688.<br />
Champely, S. and Chessel, D. (2002) Measuring biological diversity using Euclidean metrics. Environmental<br />
and Ecological Statistics, 9, 167–177.<br />
Pavoine, S., Ollier, S. and Pontier, D. (2005) Measuring diversity from dissimilarities with Rao’s<br />
quadratic entropy: are any dissimilarities suitable? <strong>The</strong>oretical Population Biology, 67, 231–239.
74 dotchart.phylog<br />
Examples<br />
par.safe
dotchart.phylog 75<br />
Usage<br />
dotchart.phylog(phylog, values, y = NULL, scaling = TRUE, ranging = TRUE, yranging<br />
joining = TRUE, yjoining = NULL, ceti = 1, cdot = 1, csub = 1,<br />
f.phylog = 1/(1 + ncol(values)), ...)<br />
Arguments<br />
phylog<br />
values<br />
y<br />
scaling<br />
ranging<br />
yranging<br />
joining<br />
an object of class phylog<br />
a vector or a data frame giving the variables<br />
a vector which values correspond to leaves positions<br />
if TRUE, data are scaled<br />
if TRUE, dotplots are drawn with the same horizontal limits<br />
a vector with two values giving the horizontal limits. If NULL, horizontal limits<br />
are defined by lower and upper values of data<br />
if TRUE, segments join each point to a central value<br />
yjoining a vector with the central value. If NULL, the central value equals 0<br />
ceti<br />
cdot<br />
csub<br />
f.phylog<br />
a character size for editing horizontal limits,<br />
used with par("cex")*ceti<br />
a character size for plotting the points of the dot plot, used with par("cex")*cdot<br />
a character size for editing the names of variables,<br />
used with par("cex")*csub<br />
a size coefficient for tree size (a parameter to draw the tree in proportion to<br />
leaves labels)<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
See Also<br />
symbols.phylog and table.phylog<br />
Examples<br />
# one variable<br />
tre
76 dotcircle<br />
par(mfrow = c(1,1))<br />
# many variables<br />
data(mjrochet)<br />
phy
doubs 77<br />
doubs<br />
Pair of Ecological Tables<br />
Description<br />
Usage<br />
Format<br />
Details<br />
<strong>Source</strong><br />
This data set gives environmental variables, fish species and spatial coordinates for 30 sites.<br />
data(doubs)<br />
doubs is a list with 3 components.<br />
mil is a data frame with 30 rows (sites) and 11 environmental variables.<br />
poi is a data frame with 30 rows (sites) and 27 fish species.<br />
xy is a data frame with 30 rows (sites) and 2 spatial coordinates.<br />
<strong>The</strong> rows of doubs$mil, doubs$poi and doubs$xy are 30 sites along the Doubs, a French<br />
and Switzerland river.<br />
doubs$mil contains the following variables: das - distance to the source (km * 10), alt - altitude<br />
(m), pen (ln(x + 1) where x is the slope (per mil * 100), deb - minimum average debit (m3/s *<br />
100), pH (* 10), dur - total hardness of water (mg/l of Calcium), pho - phosphates (mg/l * 100), nit<br />
- nitrates (mg/l * 100), amm - ammonia nitrogen (mg/l * 100), oxy - dissolved oxygen (mg/l * 10),<br />
dbo - biological demand for oxygen (mg/l * 10).<br />
doubs$poi contains the abundance of the following fish species: Cottus gobio (CHA), Salmo<br />
trutta fario (TRU), Phoxinus phoxinus (VAI), Nemacheilus barbatulus (LOC), Thymallus thymallus<br />
(OMB), Telestes soufia agassizi (BLA), Chondrostoma nasus (HOT), Chondostroma toxostoma<br />
(TOX), Leuciscus leuciscus (VAN), Leuciscus cephalus cephalus (CHE), Barbus barbus (BAR),<br />
Spirlinus bipunctatus (SPI), Gobio gobio (GOU), Esox lucius (BRO), Perca fluviatilis (PER), Rhodeus<br />
amarus (BOU), Lepomis gibbosus (PSO), Scardinius erythrophtalmus (ROT), Cyprinus carpio<br />
(CAR), Tinca tinca (TAN), Abramis brama (BCO), Ictalurus melas (PCH), Acerina cernua (GRE),<br />
Rutilus rutilus (GAR), Blicca bjoerkna (BBO), Alburnus alburnus (ABL), Anguilla anguilla (ANG).<br />
Verneaux, J. (1973) Cours d’eau de Franche-Comté (Massif du Jura). Recherches écologiques sur<br />
le réseau hydrographique du Doubs. Essai de biotypologie. Thèse d’état, Besançon. 1–257.<br />
References<br />
See a French description of fish species at http://pbil.univ-lyon1.fr/R/articles/<br />
arti049.pdf.<br />
Chesse, D., Lebreton, J.D. and Yoccoz, N.G. (1987) Propriétés de l’analyse canonique des correspondances.<br />
Une illustration en hydrobiologie. Revue de Statistique Appliquée, 35, 4, 55–72.
78 dpcoa<br />
Examples<br />
data(doubs)<br />
pca1
dpcoa 79<br />
Value<br />
option<br />
csize<br />
the function plot.dpcoa produces four graphs, option allows us to choose<br />
only some of them<br />
a size coefficient for symbols<br />
... ... further arguments passed to or from other methods<br />
Returns a list of class dpcoa containing:<br />
call<br />
nf<br />
w1<br />
w2<br />
eig<br />
RaoDiv<br />
RaoDis<br />
RaoDecodiv<br />
l1<br />
l2<br />
c1<br />
call<br />
a numeric value indicating the number of kept axes<br />
a numeric vector containing the weights of the elements<br />
a numeric vector containing the weights of the samples<br />
a numeric vector with all the eigenvalues<br />
a numeric vector containing diversities within samples<br />
an object of class dist containing the dissimilarities between samples<br />
a data frame with the decomposition of the diversity<br />
a data frame with the coordinates of the elements<br />
a data frame with the coordinates of the samples<br />
a data frame with the scores of the principal axes of the elements<br />
Author(s)<br />
Daniel Chessel<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Pavoine, S., Dufour, A.B. and Chessel, D. (2004) From dissimilarities among species to dissimilarities<br />
among communities: a double principal coordinate analysis. Journal of <strong>The</strong>oretical Biology,<br />
228, 523–537.<br />
Examples<br />
data(humDNAm)<br />
dpcoahum
80 dudi<br />
dudi<br />
Duality Diagram<br />
Description<br />
as.dudi is called by many functions (dudi.pca, dudi.coa, dudi.acm, ...) and not directly<br />
by the user. It creates duality diagrams.<br />
t.dudi returns an object of class ’dudi’ where the rows are the columns and the columns are the<br />
rows of the initial dudi.<br />
is.dudi returns TRUE if the object is of class dudi<br />
redo.dudi computes again an analysis, eventually changing the number of kept axes. Used by<br />
other functions.<br />
Usage<br />
as.dudi(df, col.w, row.w, scannf, nf, call, type, tol = 1e-07,<br />
full = FALSE)<br />
## S3 method for class 'dudi':<br />
print(x, ...)<br />
is.dudi(x)<br />
redo.dudi(dudi, newnf = 2)<br />
## S3 method for class 'dudi':<br />
t(x)<br />
Arguments<br />
df<br />
col.w<br />
row.w<br />
scannf<br />
nf<br />
call<br />
type<br />
tol<br />
full<br />
a data frame with n rows and p columns<br />
a numeric vector containing the row weights<br />
a numeric vector containing the column weights<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
generally match.call()<br />
a string of characters : the returned list will be of class c(type, "dudi")<br />
a tolerance threshold for null eigenvalues (a value less than tol times the first one<br />
is considered as null)<br />
a logical value indicating whether all non null eigenvalues should be kept<br />
x, dudi objects of class dudi<br />
... further arguments passed to or from other methods<br />
newnf<br />
an integer indicating the number of kept axes
dudi.acm 81<br />
Value<br />
as.dudi and all the functions that use it return a list with the following components :<br />
tab<br />
cw<br />
lw<br />
eig<br />
nf<br />
c1<br />
l1<br />
co<br />
li<br />
call<br />
a data frame with n rows and p columns<br />
column weights, a vector with n components<br />
row (lines) weights, a vector with p components<br />
eigenvalues, a vector with min(n,p) components<br />
integer, number of kept axes<br />
principal axes, data frame with p rows and nf columns<br />
principal components, data frame with n rows and nf columns<br />
column coordinates, data frame with p rows and nf columns<br />
row coordinates, data frame with n rows and nf columns<br />
original call<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Escoufier, Y. (1987) <strong>The</strong> duality diagram : a means of better practical applications In Development<br />
in numerical ecology, Legendre, P. & Legendre, L. (Eds.) NATO advanced Institute, Serie G.<br />
Springer Verlag, Berlin, 139–156.<br />
Examples<br />
data(deug)<br />
dd1
82 dudi.acm<br />
Usage<br />
dudi.acm (df, row.w = rep(1, nrow(df)), scannf = TRUE, nf = 2)<br />
acm.burt (df1, df2, counts = rep(1, nrow(df1)))<br />
acm.disjonctif (df)<br />
## S3 method for class 'acm':<br />
boxplot(x, xax = 1, ...)<br />
Arguments<br />
df, df1, df2 data frames containing only factors<br />
row.w, counts<br />
vector of row weights, by default, uniform weighting<br />
scannf<br />
nf<br />
x<br />
xax<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
an object of class acm<br />
the number of factor to display<br />
... further arguments passed to or from other methods<br />
Value<br />
dudi.acm returns a list of class acm and dudi (see dudi) containing<br />
cr<br />
a data frame which rows are the variables, columns are the kept scores and the<br />
values are the correlation ratios<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Tenenhaus, M. & Young, F.W. (1985) An analysis and synthesis of multiple correspondence analysis,<br />
optimal scaling, dual scaling, homogeneity analysis ans other methods for quantifying categorical<br />
multivariate data. Psychometrika, 50, 1, 91-119.<br />
Lebart, L., A. Morineau, and M. Piron. 1995. Statistique exploratoire multidimensionnelle. Dunod,<br />
Paris.<br />
See Also<br />
s.chull, s.class
dudi.coa 83<br />
Examples<br />
data(ours)<br />
summary(ours)<br />
boxplot(dudi.acm(ours, scan = FALSE))<br />
## Not run:<br />
data(banque)<br />
banque.acm
84 dudi.dec<br />
Value<br />
returns a list of class coa and dudi (see dudi) containing<br />
N<br />
the sum of all the values of the initial table<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Benzécri, J.P. and Coll. (1973) L’analyse des données. II L’analyse des correspondances, Bordas,<br />
Paris. 1–620.<br />
Greenacre, M. J. (1984) <strong>The</strong>ory and applications of correspondence analysis, Academic Press,<br />
London.<br />
Examples<br />
data(rpjdl)<br />
chisq.test(rpjdl$fau)$statistic<br />
rpjdl.coa
dudi.fca 85<br />
Arguments<br />
df<br />
eff<br />
scannf<br />
nf<br />
a data frame containing positive or null values<br />
a vector containing the reference distribution. Its length is equal to the number<br />
of rows of df<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
Value<br />
Returns a list of class dec and dudi (see dudi) containing also<br />
R<br />
sum of all the values of the initial table<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Dolédec, S., Chessel, D. and Olivier J. M. (1995) L’analyse des correspondances décentrée: application<br />
aux peuplements ichtyologiques du haut-Rhône. Bulletin Français de la Pêche et de la<br />
Pisciculture, 336, 29–40.<br />
Examples<br />
data(ichtyo)<br />
dudi1
86 dudi.fca<br />
Usage<br />
prep.fuzzy.var (df, col.blocks, row.w = rep(1, nrow(df)))<br />
dudi.fca(df, scannf = TRUE, nf = 2)<br />
dudi.fpca(df, scannf = TRUE, nf = 2)<br />
Arguments<br />
df<br />
col.blocks<br />
row.w<br />
scannf<br />
nf<br />
a data frame containing positive or null values<br />
a vector containing the number of categories for each fuzzy variable<br />
a vector of row weights<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
Value<br />
<strong>The</strong> function prep.fuzzy.var returns a data frame with the attribute col.blocks. <strong>The</strong> function<br />
dudi.fca returns a list of class fca and dudi (see dudi) containing also<br />
cr<br />
cent<br />
norm<br />
blo<br />
indica<br />
FST<br />
inertia<br />
a data frame which rows are the blocs, columns are the kept axes, and values are<br />
the correlation ratios.<br />
normal-bracket41bracket-normal<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Chevenet, F., Dolédec, S. and Chessel, D. (1994) A fuzzy coding approach for the analysis of<br />
long-term ecological data. Freshwater Biology, 31, 295–309.<br />
Examples<br />
w1
dudi.hillsmith 87<br />
data(bsetal97)<br />
w
88 dudi.mix<br />
Value<br />
Returns a list of class mix and dudi (see dudi) containing also<br />
index<br />
assign<br />
cr<br />
Author(s)<br />
a factor giving the type of each variable : f = factor, q = quantitative<br />
a factor indicating the initial variable for each column of the transformed table<br />
a data frame giving for each variable and each score:<br />
the squared correlation coefficients if it is a quantitative variable<br />
the correlation ratios if it is a factor<br />
Stephane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Hill, M. O., and A. J. E. Smith. 1976. Principal component analysis of taxonomic data with multistate<br />
discrete characters. Taxon, 25, 249-255.<br />
See Also<br />
dudi.mix<br />
Examples<br />
data(dunedata)<br />
attributes(dunedata$envir$use)$class
dudi.mix 89<br />
Details<br />
If df contains only quantitative variables, this is equivalent to a normed PCA.<br />
If df contains only factors, this is equivalent to a MCA.<br />
Ordered factors are replaced by poly(x,deg=2).<br />
This analysis generalizes the Hill and Smith method.<br />
<strong>The</strong> principal components of this analysis are centered and normed vectors maximizing the sum of<br />
the:<br />
squared correlation coefficients with quantitative variables<br />
squared multiple correlation coefficients with polynoms<br />
correlation ratios with factors.<br />
Value<br />
Returns a list of class mix and dudi (see dudi) containing also<br />
index<br />
assign<br />
cr<br />
a factor giving the type of each variable : f = factor, o = ordered, q = quantitative<br />
a factor indicating the initial variable for each column of the transformed table<br />
a data frame giving for each variable and each score:<br />
the squared correlation coefficients if it is a quantitative variable<br />
the correlation ratios if it is a factor<br />
the squared multiple correlation coefficients if it is ordered<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Hill, M. O., and A. J. E. Smith. 1976. Principal component analysis of taxonomic data with multistate<br />
discrete characters. Taxon, 25, 249-255.<br />
De Leeuw, J., J. van Rijckevorsel, and . 1980. HOMALS and PRINCALS - Some generalizations<br />
of principal components analysis. Pages 231-242 in E. Diday and Coll., editors. Data Analysis and<br />
Informatics II. Elsevier Science Publisher, North Holland, Amsterdam.<br />
Kiers, H. A. L. 1994. Simple structure in component analysis techniques for mixtures of qualitative<br />
ans quantitative variables. Psychometrika, 56, 197-212.<br />
Examples<br />
data(dunedata)<br />
dd1
90 dudi.nsc<br />
dudi.nsc<br />
Non symmetric correspondence analysis<br />
Description<br />
performs a non symmetric correspondence analysis.<br />
Usage<br />
dudi.nsc(df, scannf = TRUE, nf = 2)<br />
Arguments<br />
df<br />
scannf<br />
nf<br />
a data frame containing positive or null values<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
Value<br />
Returns a list of class nsc and dudi (see dudi) containing also<br />
N<br />
sum of the values of the initial table<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Kroonenberg, P. M., and Lombardo R. (1999) Nonsymmetric correspondence analysis: a tool for<br />
analysing contingency tables with a dependence structure. Multivariate Behavioral Research, 34,<br />
367–396.<br />
Examples<br />
data(housetasks)<br />
nsc1
dudi.pca 91<br />
dudi.pca<br />
Principal Component Analysis<br />
Description<br />
Usage<br />
dudi.pca performs a principal component analysis of a data frame and returns the results as<br />
objects of class pca and dudi.<br />
dudi.pca(df, row.w = rep(1, nrow(df))/nrow(df),<br />
col.w = rep(1, ncol(df)), center = TRUE, scale = TRUE,<br />
scannf = TRUE, nf = 2)<br />
Arguments<br />
df<br />
row.w<br />
col.w<br />
center<br />
scale<br />
scannf<br />
nf<br />
a data frame with n rows (individuals) and p columns (numeric variables)<br />
an optional row weights (by default, uniform row weights)<br />
an optional column weights (by default, unit column weights)<br />
a logical or numeric value, centring option<br />
if TRUE, centring by the mean<br />
if FALSE no centring<br />
if a numeric vector, its length must be equal to the number of columns of the<br />
data frame df and gives the decentring<br />
a logical value indicating whether the column vectors should be normed for the<br />
row.w weighting<br />
a logical value indicating whether the screeplot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
Value<br />
Returns a list of classes pca and dudi (see dudi) containing the used information for computing<br />
the principal component analysis :<br />
tab<br />
cw<br />
lw<br />
eig<br />
rank<br />
nf<br />
c1<br />
l1<br />
the data frame to be analyzed depending of the transformation arguments (center<br />
and scale)<br />
the column weights<br />
the row weights<br />
the eigenvalues<br />
the rank of the analyzed matrice<br />
the number of kept factors<br />
the column normed scores i.e. the principal axes<br />
the row normed scores
92 dudi.pco<br />
co<br />
li<br />
call<br />
cent<br />
norm<br />
the column coordinates<br />
the row coordinates i.e. the principal components<br />
the call function<br />
the p vector containing the means for variables<br />
the p vector containing the standard deviations for variables i.e. the root of the<br />
sum of squares deviations of the values from their means divided by n<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
See Also<br />
prcomp, princomp in the mva library<br />
Examples<br />
data(deug)<br />
deug.dudi
dudi.pco 93<br />
Usage<br />
dudi.pco(d, row.w = "uniform", scannf = TRUE, nf = 2,<br />
full = FALSE, tol = 1e-07)<br />
## S3 method for class 'pco':<br />
scatter(x, xax = 1, yax = 2, clab.row = 1, posieig = "top",<br />
sub = NULL, csub = 2, ...)<br />
Arguments<br />
d<br />
row.w<br />
scannf<br />
nf<br />
full<br />
tol<br />
x<br />
xax<br />
yax<br />
clab.row<br />
posieig<br />
sub<br />
csub<br />
an object of class dist containing a Euclidean distance matrix.<br />
an optional distance matrix row weights. If not NULL, must be a vector of<br />
positive numbers with length equal to the size of the distance matrix<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
a logical value indicating whether all the axes should be kept<br />
a tolerance threshold to test whether the distance matrix is Euclidean : an eigenvalue<br />
is considered positive if it is larger than -tol*lambda1 where lambda1<br />
is the largest eigenvalue.<br />
an object of class pco<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
a character size for the row labels<br />
if "top" the eigenvalues bar plot is upside, if "bottom" it is downside, if "none"<br />
no plot<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
... further arguments passed to or from other methods<br />
Value<br />
dudi.pco returns a list of class pco and dudi. See dudi<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Gower, J. C. (1966) Some distance properties of latent root and vector methods used in multivariate<br />
analysis. Biometrika, 53, 325–338.
94 dunedata<br />
Examples<br />
data(yanomama)<br />
gen
ecg 95<br />
ecg<br />
Electrocardiogram data<br />
Description<br />
Usage<br />
Format<br />
<strong>Source</strong><br />
<strong>The</strong>se data were measured during the normal sinus rhythm of a patient who occasionally experiences<br />
arrhythmia. <strong>The</strong>re are 2048 observations measured in units of millivolts and collected at a rate of<br />
180 samples per second. This time series is a good candidate for a multiresolution analysis because<br />
its components are on different scales. For example, the large scale (low frequency) fluctuations,<br />
known as baseline drift, are due to the patient respiration, while the prominent short scale (high<br />
frequency) intermittent fluctuations between 3 and 4 seconds are evidently due to patient movement.<br />
Heart rhythm determines most of the remaining features in the series. <strong>The</strong> large spikes occurring<br />
about 0.7 seconds apart the R waves of normal heart rhythm; the smaller, but sharp peak coming<br />
just prior to an R wave is known as a P wave; and the broader peak that comes after a R wave is a T<br />
wave.<br />
data(ecg)<br />
A vector of class ts containing 2048 observations.<br />
Gust Bardy and Per Reinhall, University of Washington<br />
References<br />
Percival, D. B., and Walden, A.T. (2000) Wavelet Methods for Time Series Analysis, Cambridge<br />
University Press.<br />
Examples<br />
## Not run:<br />
# figure 130 in Percival and Walden (2000)<br />
if (require(waveslim) == TRUE) {<br />
data(ecg)<br />
ecg.level
96 ecomor<br />
}<br />
## End(Not run)<br />
ecomor<br />
Ecomorphological Convergence<br />
Description<br />
This data set gives ecomorphological informations about 129 bird species.<br />
Usage<br />
data(ecomor)<br />
Format<br />
ecomor is a list of 7 components.<br />
forsub is a data frame with 129 species, 6 variables (the feeding place classes): foliage, ground ,<br />
twig , bush, trunk and aerial feeders. <strong>The</strong>se dummy variables indicate the use (1) or no use (0)<br />
of a given feeding place by a species.<br />
diet is a data frame with 129 species and 8 variables (diet types): Gr (granivorous: seeds), Fr<br />
(frugivorous: berries, acorns, drupes), Ne (frugivorous: nectar), Fo (folivorous: leaves), In<br />
(invertebrate feeder: insects, spiders, myriapods, isopods, snails, worms), Ca (carnivorous:<br />
flesh of small vertebrates), Li (limnivorous: invertebrates in fresh water), and Ch (carrion<br />
feeder). <strong>The</strong>se dummy variables indicate the use (1) or no use (0) of a given diet type by a<br />
species.<br />
habitat is a data frame with 129 species, 16 dummy variables (the habitats). <strong>The</strong>se variables<br />
indicate the species presence (1) or the species absence (0) in a given habitat.<br />
morpho is a data frame with 129 species abd 8 morphological variables: wingl (Wing length, mm),<br />
taill (Tail length, mm), culml (Culmen length, mm), bilh (Bill height, mm), bilw (Bill width,<br />
mm), tarsl (Tarsus length, mm), midtl (Middle toe length, mm) and weig (Weight, g).<br />
taxo is a data frame with 129 species and 3 factors: Genus, Family and Order. It is a data frame of<br />
class ’taxo’: the variables are factors giving nested classifications.<br />
labels is a data frame with vectors of the names of species (complete and in abbreviated form.<br />
categ is a data frame with 129 species, 2 factors : ’forsub’ summarizing the feeding place and ’diet’<br />
the diet type.<br />
<strong>Source</strong><br />
Blondel, J., Vuilleumier, F., Marcus, L.F., and Terouanne, E. (1984). Is there ecomorphological<br />
convergence among mediterranean bird communities of Chile, California, and France. In Evolutionary<br />
Biology (eds M.K. Hecht, B. Wallace and R.J. MacIntyre), 141–213, 18. Plenum Press,<br />
New York.
elec88 97<br />
References<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps023.pdf (in French).<br />
Examples<br />
data(ecomor)<br />
ric
98 elec88<br />
Format<br />
elec88 is a list of 7 components.<br />
tab is a data frame with 94 rows (departments) and 9 variables (candidates)<br />
res is the global result of the election all-over the country.<br />
lab is a data frame with three variables: elec88$lab$dep a vector containing the names of the<br />
94 french departments, elec88$lab$reg a vector containing the names of the 21 French<br />
administraitve regions. and, elec88$lab$reg.fac a factor with 21 levels defining the<br />
French administraitve regions.<br />
area is the data frame of 3 variables returning the boundary lines of each department. <strong>The</strong> first<br />
variable is a factor. <strong>The</strong> levels of this one are the row.names of tab. <strong>The</strong> second and third<br />
variables return the coordinates (x,y) of the points of the boundary line.<br />
contour is a data frame with 4 variables (x1,y1,x2,y2)for the contour display of France<br />
xy is a data frame with two variables (x,y) giving the position of the center for each department<br />
neig is the neighbouring graph between departments, object of the class neig<br />
<strong>Source</strong><br />
Public data<br />
See Also<br />
This dataset is compatible with presid2002 and cnc2003<br />
Examples<br />
data(elec88)<br />
apply(elec88$tab, 2, mean)<br />
summary(elec88$res)<br />
par(mfrow = c(2,2))<br />
plot(elec88$area[,2:3], type = "n", asp = 1)<br />
lpoly
escopage 99<br />
escopage<br />
K-tables of wine-tasting<br />
Description<br />
Usage<br />
Format<br />
<strong>Source</strong><br />
This data set describes 27 characteristics of 21 wines distributed in four fields : rest, visual, olfactory<br />
and global.<br />
data(escopage)<br />
escopage is a list of 3 components.<br />
tab is a data frame with 21 observations (wines) and 27 variables.<br />
tab.names is the vector of the names of sub-tables : "rest" "visual" "olfactory" "global".<br />
blo is a vector of the numbers of variables for each sub-table.<br />
Escofier, B. and Pagès, J. (1990) Analyses factorielles simples et multiples : objectifs, méthodes et<br />
interprétation Dunod, Paris. 1–267.<br />
Escofier, B. and Pagès, J. (1994) Multiple factor analysis (AFMULT package). Computational<br />
Statistics and Data Analysis, 18, 121–140.<br />
Examples<br />
data(escopage)<br />
w
100 fission<br />
Format<br />
<strong>Source</strong><br />
euro123 is a list of 4 components.<br />
in78 is a data frame with 12 rows and 3 variables.<br />
in86 : idem in 1986<br />
in97 : idem in 1997<br />
plan is a data frame with two factors to both organize the 3 tables.<br />
Encyclopaedia Universalis, Symposium, Les chiffres du Monde. Encyclopaedia Universalis, Paris.<br />
519.<br />
Université de Barcelone : http://www.ub.es/medame/nutstat1.html<br />
Examples<br />
data(euro123)<br />
par(mfrow = c(2,2))<br />
triangle.plot(euro123$in78, addaxes = TRUE)<br />
triangle.plot(euro123$in86, addaxes = TRUE)<br />
triangle.plot(euro123$in97, addaxes = TRUE)<br />
triangle.biplot(euro123$in78, euro123$in97)<br />
par(mfrow = c(1,1))<br />
fission<br />
Fission pattern and heritable morphological traits<br />
Description<br />
This data set contains the mean values of five highly heritable linear combinations of cranial metric<br />
(GM1-GM3) and non metric (GN1-GN2) for 8 social groups of Rhesus Macaques on Cayo<br />
Santiago. It also describes the fission tree depicting the historical phyletic relationships.<br />
Usage<br />
data(fission)<br />
Format<br />
fission is a list containing the 2 following objects :<br />
tre is a character string giving the fission tree in Newick format.<br />
tab is a data frame with 8 social groups and five traits : cranial metrics (GM1, GM2, GM3) and<br />
cranial non metrics (GN1, GN2)
foucart 101<br />
References<br />
Cheverud, J. and Dow, M.M. (1985) An autocorrelation analysis of genetic variation due to lineal<br />
fission in social groups of rhesus macaques. American Journal of Physical Anthropology, 67, 113–<br />
122.<br />
Examples<br />
data(fission)<br />
fis.phy
102 foucart<br />
Value<br />
foucart returns a list of the classes ’dudi’, ’coa’ and ’foucart’<br />
call<br />
nf<br />
rank<br />
blo<br />
cw<br />
lw<br />
eig<br />
tab<br />
li<br />
l1<br />
co<br />
c1<br />
Tli<br />
Tco<br />
TL<br />
TC<br />
origine<br />
axes-components saved<br />
rank<br />
useful vector<br />
vector: column weights<br />
vector: row weights<br />
vector: eigen values<br />
data.frame: modified array<br />
data.frame: row coordinates<br />
data.frame: row normed scores<br />
data.frame: column coordinates<br />
data.frame: column normed scores<br />
data.frame: row coordinates (each table)<br />
data.frame: col coordinates (each table)<br />
data.frame: factors for Tli<br />
data.frame: factors for Tco<br />
Author(s)<br />
P. Bady 〈pierre.bady@univ-lyon1.fr〉<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Foucart, T. (1984) Analyse factorielle de tableaux multiples, Masson, Paris.<br />
Examples<br />
data(bf88)<br />
fou1
friday87 103<br />
friday87<br />
Faunistic K-tables<br />
Description<br />
Usage<br />
Format<br />
<strong>Source</strong><br />
This data set gives informations about sites, species and environmental variables.<br />
data(friday87)<br />
friday87 is a list of 4 components.<br />
fau is a data frame containing a faunistic table with 16 sites and 91 species.<br />
mil is a data frame with 16 sites and 11 environmental variables.<br />
fau.blo is a vector of the number of species per group.<br />
tab.names is the name of each group of species.<br />
Friday, L.E. (1987) <strong>The</strong> diversity of macroinvertebrate and macrophyte communities in ponds,<br />
Freshwater Biology, 18, 87–104.<br />
Examples<br />
data(friday87)<br />
wfri
104 fruits<br />
Format<br />
Details<br />
fruits is a list of 3 components:<br />
typ is a vector returning the type of the 28 batches of fruits (peaches or nectarines).<br />
jug is a data frame of 28 rows and 16 columns (judges).<br />
var is a data frame of 28 rows and 16 measures (average of 2 judgements).<br />
fruits$var is a data frame of 15 variables:<br />
taches : quantity of cork blemishes (0=absent - maximum 5)<br />
stries : quantity of stria (1/none - maximum 4)<br />
abmucr : abundance of mucron (1/absent - 4)<br />
irform : shape irregularity (0/none - 3)<br />
allong : length of the fruit (1/round fruit - 4)<br />
suroug : percentage of the red surface (minimum 40% - maximum 90%)<br />
homlot : homogeneity of the intra-batch coloring (1/strong - 4)<br />
homfru : homogeneity of the intra-fruit coloring (1/strong - 4)<br />
pubesc : pubescence (0/none - 4)<br />
verrou : intensity of green in red area (1/none - 4)<br />
foncee : intensity of dark area (0/pink - 4)<br />
comucr : intensity of the mucron color (1=no contrast - 4/dark)<br />
impres : kind of impression (1/watched - 4/pointillé)<br />
coldom : intensity of the predominating color (0/clear - 4)<br />
calibr : grade (1/200g)<br />
<strong>Source</strong><br />
Kervella, J. (1991) Analyse de l’attrait d’un produit : exemple d’une comparaison de lots de pêches.<br />
Agro-Industrie et méthodes statistiques. Compte-rendu des secondes journées européennes. Nantes<br />
13-14 juin 1991. Association pour la Statistique et ses Utilisations, Paris, 313–325.<br />
Examples<br />
data(fruits)<br />
par(mfrow = c(2,2))<br />
pcajug
fuzzygenet 105<br />
fuzzygenet<br />
Reading a table of genetic data (diploid individuals)<br />
Description<br />
Reads data like char2genet without a priori population<br />
Usage<br />
fuzzygenet(X)<br />
Arguments<br />
X<br />
a data frame of strings of characters (individuals in row, locus in variables), the<br />
value coded ’000000’ or two alleles of 6 characters<br />
Details<br />
Value<br />
In entry, a row is an individual, a variable is a locus and a value is a string of characters, for example,<br />
012028 for a heterozygote carying alleles 012 and 028; 020020 for a homozygote carrying two<br />
alleles 020 and 000000 for a not classified locus (missing data).<br />
In exit, a fuzzy array with the following encoding for a locus:<br />
0 0 1 . . . 0 for a homozygote<br />
0 0.5 0.5 . . . 0 for a heterozygote<br />
p1 p2 p3 . . . pm for an unknown where (p1 p2 p3 . . . pm) is the observed allelic frequencies for all<br />
tha available data.<br />
returns a data frame with the 6 following attributs:<br />
col.blocks<br />
all.names<br />
loc.names<br />
row.w<br />
col.freq<br />
col.num<br />
a vector containing the number of alleles by locus<br />
a vector containing the names of alleles<br />
a vector containing the names of locus<br />
a vector containing the uniform weighting of rows<br />
a vector containing the global allelic frequencies<br />
a factor ranking the alleles by locus<br />
Note<br />
In the exit data frame, the alleles are numbered 1, 2, 3, . . . by locus and the loci are called L01, L02,<br />
L03, . . . for the simplification of listing. <strong>The</strong> original names are kept.<br />
Author(s)<br />
Daniel Chessel
106 gearymoran<br />
References<br />
See Also<br />
put references to the literature/web site here<br />
char2genet if you have the a priori definition of the groups of individuals (populations). It may<br />
be used on the created object dudi.fca<br />
Examples<br />
data(casitas)<br />
casitas[1:5, ]<br />
casitas
genet 107<br />
Value<br />
Returns an object of class krandtest (randomization tests).<br />
Author(s)<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
Daniel Chessel<br />
References<br />
Cliff, A. D. and Ord, J. K. (1973) Spatial autocorrelation, Pion, London.<br />
Thioulouse, J., Chessel, D. and Champely, S. (1995) Multivariate analysis of spatial patterns: a<br />
unified approach to local and global structures. Environmental and Ecological Statistics, 2, 1–14.<br />
See Also<br />
moran.test and geary.test for classical versions of Moran’s test and Geary’s one<br />
Examples<br />
# a spatial example<br />
data(mafragh)<br />
tab0
108 genet<br />
Description<br />
<strong>The</strong>re are multiple formats of genetic data. <strong>The</strong> functions of <strong>ade4</strong> associated genetic data use the<br />
class genet. An object of the class genet is a list containing at least one data frame whose<br />
lines are groups of individuals (populations) and columns alleles forming blocks associated with<br />
the locus. <strong>The</strong>y contain allelic frequencies expressed as a percentage.<br />
<strong>The</strong> function char2genet ensures the reading of tables crossing diploid individuals arranged by<br />
groups (populations) and polymorphic loci. Data frames containing only strings of characters are<br />
transformed in tables of allelic frequencies of the class genet. In entry a row is an individual, a<br />
variable is a locus and a value is a string of characters, for example ’ 012028 ’ for a heterozygote<br />
carrying alleles 012 and 028, ’ 020020 ’ for a homozygote carrying two alleles 020 and ’ 000000 ’<br />
for a not classified locus (missing data).<br />
<strong>The</strong> function count2genet reads data frames containing allelic countings by populations and<br />
allelic forms classified by locus.<br />
<strong>The</strong> function freq2genet reads data frames containing allelic frequencies by populations and<br />
allelic forms classified by locus.<br />
In these two cases, use as names of variables of strings of characters xx.yyy where xx are the<br />
names of locus and yyy a name of allelic forms in this locus. <strong>The</strong> analyses on this kind of data<br />
having to use compact labels, these functions classify the names of the populations, the names of<br />
the loci and the names of the allelic forms in vectors and re-code in a simple way starting with P for<br />
population, L for locus and 1,. . . , m for the alleles.<br />
Usage<br />
char2genet(X, pop, complete)<br />
count2genet(PopAllCount)<br />
freq2genet(PopAllFreq)<br />
Arguments<br />
X<br />
pop<br />
complete<br />
PopAllCount<br />
PopAllFreq<br />
a data frame of strings of characters (individuals in row, locus in variables), the<br />
value coded ’000000’ or two alleles of 6 characters<br />
a factor with the same number of rows than df classifying the individuals by<br />
population<br />
a logical value indicating a complete issue or not, by default FALSE<br />
a data frame containing integers: the occurrences of each allelic form (column)<br />
in each population (row)<br />
a data frame containing values between 0 and 1: the frequencies of each allelic<br />
form (column) in each population (row)<br />
Details<br />
As a lot of formats for genetic data are published in literature, a list of class genet contains at<br />
least a table of allellic frequencies and an attribut loc.blocks. <strong>The</strong> populations (row) and the<br />
variables (column) are classified by alphabetic order. In the component comp, each individual per<br />
locus of m alleles is re-coded by a vector of length m: for hererozygicy 0,. . . ,1,. . . ,1,. . . ,0 and<br />
homozygocy 0,. . . ,2,0.
genet 109<br />
Value<br />
char2genet returns a list of class genet with :<br />
$tab<br />
$center<br />
a frequencies table of poplations (row) and alleles (column)<br />
the global frequency of each allelic form calculated on the overall individuals<br />
classified on each locus<br />
$pop.names a vector containing the names of populations present in the data re-coded P01,<br />
P02, . . .<br />
$all.names<br />
$loc.blocks<br />
$loc.fac<br />
$loc.names<br />
$pop.loc<br />
$comp<br />
$comp.pop<br />
a vector containing the names of the alleles present in the data re-coded L01.1,<br />
L01.2, . . .<br />
a vector containing the number of alleles by loci<br />
a factor sharing the alleles by loci<br />
a vector containing the names of loci present in the data re-coded L01, . . . , L99<br />
a data frame containing the number of genus allowing the calculation of frequencies<br />
the complete individual typing with the code 02000 or 01001 if the option<br />
complete is TRUE<br />
a factor indicating the population if the option complete is TRUE<br />
count2genet and freq2genet return a list of class genet which don’t contain the components<br />
pop.loc and complete.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(casitas)<br />
casitas[24,]<br />
casitas.pop
110 ggtortoises<br />
casitas.coa
granulo 111<br />
Examples<br />
if(require(pixmap, quiet=TRUE)){<br />
data(ggtortoises)<br />
a1
112 gridrowcol<br />
gridrowcol<br />
Complete regular grid analysis<br />
Description<br />
This function defines objects to analyse data sets associated with complete regular grid.<br />
Usage<br />
gridrowcol(nrow, ncol, cell.names = NULL)<br />
Arguments<br />
nrow<br />
ncol<br />
cell.names<br />
size of the grid (number of rows)<br />
size of the grid (number of columns)<br />
grid cell labels<br />
Value<br />
Returns a list containing the following items :<br />
xy<br />
area<br />
neig<br />
orthobasis<br />
: a data frame with grid cell coordinates<br />
: a data frame with three variables to display grid cells as areas<br />
: an object of class ’neig’ corresponding to a neighbouring graph of the grid<br />
(rook case)<br />
: an object of class ’orthobasis’ corresponding to the analytical solution<br />
for the neighbouring graph<br />
Author(s)<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
Daniel Chessel<br />
References<br />
Méot, A., Chessel, D. and Sabatier, D. (1993) Opérateurs de voisinage et analyse des données<br />
spatio-temporelles. in J.D. Lebreton and B. Asselain, editors. Biométrie et environnement. Masson,<br />
45-72.<br />
Cornillon, P.A. (1998) Prise en compte de proximités en analyse factorielle et comparative. Thèse,<br />
Ecole Nationale Supérieure Agronomique, Montpellier.<br />
See Also<br />
orthobasis, orthogram, mld
hdpg 113<br />
Examples<br />
w
114 housetasks<br />
Details<br />
<strong>The</strong> rows of hdpg$pop are the names of the 52 populations belonging to the geographic regions<br />
contained in the rows of hdpg$region. <strong>The</strong> chosen regions are: America, Asia, Europe, Middle<br />
East North Africa, Oceania, Subsaharan AFRICA.<br />
<strong>The</strong> 52 populations are: Adygei, Balochi, Bantu, Basque, Bedouin, Bergamo, Biaka Pygmies,<br />
Brahui, Burusho, Cambodian, Columbian, Dai, Daur, Druze, French, Han, Hazara, Hezhen, Japanese,<br />
Kalash, Karitiana, Lahu, Makrani, Mandenka, Maya, Mbuti Pygmies, Melanesian, Miaozu, Mongola,<br />
Mozabite, Naxi, NewGuinea, Nilote, Orcadian, Oroqen, Palestinian, Pathan, Pima, Russian,<br />
San, Sardinian, She, Sindhi, Surui, Tu, Tujia, Tuscan, Uygur, Xibo, Yakut, Yizu, Yoruba.<br />
hdpg$freq is a data frame with 52 rows, corresponding to the 52 populations described above,<br />
and 4992 microsatellite markers.<br />
<strong>Source</strong><br />
Extract of data prepared by the Human Diversity Panel Genotypes http://research.marshfieldclinic.<br />
org/genetics/Freq/FreqInfo.htm<br />
prepared by Hinda Haned, from data used in: Noah A. Rosenberg, Jonatahan K. Pritchard, James<br />
L. Weber, Howard M. Cabb, Kenneth K. Kidds, Lev A. Zhivotovsky, Marcus W. Feldman (2002)<br />
Genetic Structure of human Populations Science, 298, 2381–2385.<br />
Lev A. Zhivotovsky, Noah Rosenberg, and Marcus W. Feldman (2003). Features of Evolution and<br />
Expansion of Modern Humans, Inferred from Genomewide Microsatellite Markers Am. J. Hum.<br />
Genet, 72, 1171–1186.<br />
Examples<br />
## Not run:<br />
library(<strong>ade4</strong>)<br />
data(hdpg)<br />
freq
humDNAm 115<br />
Usage<br />
data(housetasks)<br />
Format<br />
This data frame contains four columns : wife, alternating, husband and jointly. Each column is a<br />
numeric vector.<br />
<strong>Source</strong><br />
Kroonenberg, P. M. and Lombardo, R. (1999) Nonsymmetric correspondence analysis: a tool for<br />
analysing contingency tables with a dependence structure. Multivariate Behavioral Research, 34,<br />
367–396<br />
Examples<br />
data(housetasks)<br />
nsc1
116 ichtyo<br />
<strong>Source</strong><br />
Excoffier, L., Smouse, P.E. and Quattro, J.M. (1992) Analysis of molecular variance inferred from<br />
metric distances among DNA haplotypes: application to human mitochondrial DNA restriction<br />
data. Genetics, 131, 479–491.<br />
Examples<br />
data(humDNAm)<br />
dpcoahum
inertia.dudi 117<br />
inertia.dudi<br />
Statistics of inertia in a one-table analysis<br />
Description<br />
Prints of the statistics of inertia in a one-table analysis<br />
Usage<br />
inertia.dudi(dudi, row.inertia = FALSE, col.inertia = FALSE)<br />
Arguments<br />
dudi<br />
row.inertia<br />
col.inertia<br />
a duality diagram, object of class dudi<br />
if TRUE, returns the statistics of the decomposition of inertia for the rows<br />
if TRUE, returns the statistics of the decomposition of inertia for the columns<br />
Details<br />
Contributions are printed in 1/10000 and the sign is the sign of the coordinate<br />
Value<br />
a list containing :<br />
TOT<br />
row.abs<br />
row.rel<br />
row.cum<br />
col.abs<br />
col.rel<br />
col.cum<br />
repartition of the total inertia between axes<br />
absolute contributions of the decomposition of inertia for the rows<br />
relative contributions of the decomposition of inertia for the rows<br />
cumulative relative contributions of the decomposition of inertia for the rows<br />
absolute contributions of the decomposition of inertia for the columns<br />
relative contributions of the decomposition of inertia for the columns<br />
cumulative relative contributions of the decomposition of inertia for the columns<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉
118 irishdata<br />
References<br />
Lebart, L., Morineau, A. and Tabart, N. (1977) Techniques de la description statistique, méthodes<br />
et logiciels pour la description des grands tableaux, Dunod, Paris, 61–62.<br />
Volle, M. (1981) Analyse des données, Economica, Paris, 89–90 and 118<br />
Lebart, L., Morineau, L. and Warwick, K.M. (1984) Multivariate descriptive analysis: correspondence<br />
and related techniques for large matrices, John Wiley and Sons, New York.<br />
Greenacre, M. (1984) <strong>The</strong>ory and applications of correspondence analysis, Academic Press, London,<br />
66.<br />
Rouanet, H. and Le Roux, B. (1993) Analyse des données multidimensionnelles, Dunod, Paris,<br />
143–144.<br />
Tenenhaus, M. (1994) Méthodes statistiques en gestion, Dunod, Paris, p. 160, 161, 166, 204.<br />
Lebart, L., Morineau, A. and Piron, M. (1995) Statistique exploratoire multidimensionnelle, Dunod,<br />
Paris, p. 56,95-96.<br />
Examples<br />
data(housetasks)<br />
coa1
is.euclid 119<br />
contour is a data frame with the global polygon of all the 25 counties.<br />
link is a matrix containing the common length between two counties from area.<br />
area.utm is a data frame with polygons for each of the 25 contiguous counties expressed in Universal<br />
Transverse Mercator (UTM) coordinates.<br />
xy.utm is a data frame with the UTM coordinates centers of the 25 counties.<br />
link.utm is a matrix containing the common length between two counties from area.utm.<br />
tab.utm is a data frame with the 25 counties (explicitly named) and 12 variables.<br />
contour.utm is a data frame with the global polygon of all the 25 counties expressed in UTM<br />
coordinates.<br />
<strong>Source</strong><br />
Geary, R.C. (1954) <strong>The</strong> contiguity ratio and statistical mapping. <strong>The</strong> incorporated Statistician, 5,<br />
3, 115–145.<br />
Cliff, A.D. and Ord, J.K. (1973) Spatial autocorrelation, Pion, London. 1–178.<br />
Examples<br />
data(irishdata)<br />
par(mfrow = c(2,2))<br />
area.plot(irishdata$area, lab = irishdata$county.names, clab = 0.75)<br />
area.plot(irishdata$area)<br />
apply(irishdata$contour, 1, function(x) segments(x[1],x[2],x[3],x[4],<br />
lwd = 3))<br />
s.corcircle(dudi.pca(irishdata$tab, scan = FALSE)$co)<br />
score
120 julliot<br />
Arguments<br />
Value<br />
distmat<br />
plot<br />
print<br />
tol<br />
object<br />
an object of class ’dist’<br />
a logical value indicating whether the eigenvalues bar plot of the matrix of the<br />
term − 1 2 d2 ij centred by rows and columns should be diplayed<br />
a logical value indicating whether the eigenvalues of the matrix of the term<br />
− 1 2 d2 ij centred by rows and columns should be printed<br />
a tolerance threshold : an eigenvalue is considered positive if it is larger than<br />
-tol*lambda1 where lambda1 is the largest eigenvalue.<br />
an object of class ’dist’<br />
... further arguments passed to or from other methods<br />
returns a logical value indicating if all the eigenvalues are positive or equal to zero<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Gower, J.C. and Legendre, P. (1986) Metric and Euclidean properties of dissimilarity coefficients.<br />
Journal of Classification, 3, 5–48.<br />
Examples<br />
w
julliot 121<br />
Format<br />
julliot is a list containing the 3 following objects :<br />
tab is a data frame with 160 rows (quadrats) and 7 variables (species).<br />
xy is a data frame with the coordinates of the 160 quadrats (positioned by their centers).<br />
area is a data frame with 3 variables returning the boundary lines of each quadrat. <strong>The</strong> first variable<br />
is a factor. <strong>The</strong> levels of this one are the row.names of tab. <strong>The</strong> second and third variables<br />
return the coordinates (x,y) of the points of the boundary line.<br />
Species names of julliot$tab are Pouteria torta, Minquartia guianensis, Quiina obovata,<br />
Chrysophyllum lucentifolium, Parahancornia fasciculata, Virola michelii, Pourouma spp.<br />
References<br />
Julliot, C. (1992) Utilisation des ressources alimentaires par le singe hurleur roux, Alouatta seniculus<br />
(Atelidae, Primates), en Guyane : impact de la dissémination des graines sur la régénération<br />
forestière. Thèse de troisième cycle, Université de Tours.<br />
Julliot, C. (1997) Impact of seed dispersal by red howler monkeys Alouatta seniculus on the seedling<br />
population in the understorey of tropical rain forest. Journal of Ecology, 85, 431–440.<br />
Examples<br />
data(julliot)<br />
par(mfrow = c(3,3))<br />
## Not run:<br />
for(k in 1:7)<br />
area.plot(julliot$area,val = log(julliot$tab[,k]+1),<br />
sub = names(julliot$tab)[k], csub = 2.5)<br />
## End(Not run)<br />
if (require(splancs, quiet = TRUE)){<br />
par(mfrow = c(3,3))<br />
for(k in 1:7)<br />
s.image(julliot$xy, log(julliot$tab[,k]+1), kgrid = 3, span = 0.25,<br />
sub = names(julliot$tab)[k], csub = 2.5)<br />
}<br />
## Not run:<br />
par(mfrow = c(3,3))<br />
for(k in 1:7) {<br />
area.plot(julliot$area)<br />
s.value(julliot$xy, scalewt(log(julliot$tab[,k]+1)),<br />
sub = names(julliot$tab)[k],csub = 2.5, add.p = TRUE)<br />
}<br />
## End(Not run)<br />
par(mfrow = c(3,3))<br />
for(k in 1:7)<br />
s.value(julliot$xy,log(julliot$tab[,k]+1),<br />
sub = names(julliot$tab)[k], csub = 2.5)<br />
## Not run:
122 jv73<br />
if (require(spdep, quiet = TRUE)){<br />
par(mfrow = c(1,1))<br />
neig0
kcponds 123<br />
Examples<br />
data(jv73)<br />
s.label(jv73$xy, contour = jv73$contour, incl = FALSE,<br />
clab = 0.75)<br />
s.class(jv73$xy, jv73$fac.riv, add.p = TRUE, cell = 0,<br />
axese = FALSE, csta = 0, cpoi = 0, clab = 1.25)<br />
w
124 kdist<br />
Examples<br />
data(kcponds)<br />
par(mfrow=c(3,1))<br />
area.plot(kcponds$area)<br />
s.label(kcponds$xy,add.p = TRUE, cpoi = 2, clab = 0)<br />
s.label(kcponds$xy,add.p = TRUE, cpoi = 3, clab = 0)<br />
s.label(kcponds$xy,add.p = TRUE, cpoi = 0, clab = 0,<br />
neig = kcponds$neig, cneig = 1)<br />
area.plot(kcponds$area)<br />
s.label(kcponds$xy, add.p = TRUE, clab = 1.5)<br />
w
kdist 125<br />
Details<br />
<strong>The</strong> attributs of a ’kdist’ object are:<br />
names: the names of the distances<br />
size: the number of points between distances are known<br />
labels: the labels of points<br />
euclid: a logical vector indicating whether each distance of the list is Euclidean or not.<br />
call: a call order<br />
class: object ’kdist’<br />
Value<br />
returns an object of class ’kdist’ containing a list of semidefinite matrices.<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Gower, J. C. (1966) Some distance properties of latent root and vector methods used in multivariate<br />
analysis. Biometrika, 53, 325–338.<br />
Examples<br />
# starting from a list of matrices<br />
data(yanomama)<br />
lapply(yanomama,class)<br />
kd1 = kdist(yanomama)<br />
print(kd1)<br />
# giving the correlations of Mantel's test<br />
cor(as.data.frame(kd1))<br />
pairs(as.data.frame(kd1))<br />
# starting from a list of objects 'dist'<br />
data(friday87)<br />
fri.w
126 kdist2ktab<br />
d3
kdisteuclid 127<br />
Value<br />
returns a list of class ktab containing for each distance of kd the data frame of its Euclidean<br />
representation<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
Examples<br />
data(friday87)<br />
fri.w
128 kdisteuclid<br />
Value<br />
returns an object of class kdist with all distances Euclidean.<br />
Note<br />
according to the program DistPCoa of P. Legendre and M.J. Anderson<br />
http://www.fas.umontreal.ca/BIOL/Casgrain/en/labo/distpcoa.html<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Gower, J.C. and Legendre, P. (1986) Metric and Euclidean properties of dissimilarity coefficients.<br />
Journal of Classification, 3, 5–48.<br />
Cailliez, F. (1983) <strong>The</strong> analytical solution of the additive constant problem. Psychometrika, 48,<br />
305–310.<br />
Lingoes, J.C. (1971) Somme boundary conditions for a monotone analysis of symmetric matrices.<br />
Psychometrika, 36, 195–203.<br />
Legendre, P. and Anderson, M.J. (1999) Distance-based redundancy analysis: testing multispecies<br />
responses in multifactorial ecological experiments. Ecological Monographs, 69, 1–24.<br />
Legendre, P., and L. Legendre. (1998) Numerical ecology, 2nd English edition edition. Elsevier<br />
Science BV, Amsterdam.<br />
Examples<br />
w
kplot 129<br />
kplot<br />
Generic Function for Multiple Graphs in a K-tables Analysis<br />
Description<br />
Usage<br />
Methods for foucart, mcoa, mfa, pta, sepan, sepan.coa and statis<br />
kplot(object, ...)<br />
Arguments<br />
object<br />
an object used to select a method<br />
... further arguments passed to or from other methods<br />
Examples<br />
methods(plot)<br />
methods(scatter)<br />
methods(kplot)<br />
kplot.foucart<br />
Multiple Graphs for the Foucart’s Correspondence Analysis<br />
Description<br />
Usage<br />
performs high level plots of a Foucart’s Correspondence Analysis, using an object of class foucart.<br />
## S3 method for class 'foucart':<br />
kplot(object, xax = 1, yax = 2, mfrow = NULL,<br />
which.tab = 1:length(object$blo), clab.r = 1, clab.c = 1.25,<br />
csub = 2, possub = "bottomright", ...)<br />
Arguments<br />
object<br />
xax, yax<br />
mfrow<br />
which.tab<br />
clab.r<br />
an object of class foucart<br />
the numbers of the x-axis and the y-axis<br />
a vector of the form ’c(nr,nc)’, otherwise computed by as special own function<br />
n2mfrow<br />
vector of table numbers for analyzing<br />
a character size for the row labels
130 kplot.mcoa<br />
clab.c<br />
csub<br />
possub<br />
a character size for the column labels<br />
a character size for the sub-titles used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(bf88)<br />
fou1
kplot.mfa 131<br />
csub<br />
possub<br />
a character size for the sub-titles, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(friday87)<br />
w1
132 kplot.pta<br />
col.names<br />
a logical value indicating whether the column labels should be inserted<br />
traject a logical value indicating whether the trajectories of the rows should be drawn<br />
in a natural order<br />
permute.row.col<br />
if TRUE, the rows are represented by vectors and columns by points, otherwise<br />
it is the opposite<br />
clab<br />
csub<br />
possub<br />
a character size for the labels<br />
a character size for the sub-titles, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(friday87)<br />
w1
kplot.sepan 133<br />
which.graph<br />
an option for drawing, an integer between 1 and 4. For each table of which.tab,<br />
are drawn :<br />
1 the projections of the principal axes<br />
2 the projections of the rows<br />
3 the projections of the columns<br />
4 the projections of the principal components onto the planes of the compromise<br />
clab<br />
cpoint<br />
csub<br />
possub<br />
ask<br />
a character size for the labels<br />
a character size for plotting the points, used with par("cex")*cpoint. If zero,<br />
no points are drawn.<br />
a character size for the sub-titles, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
a logical value indicating if the graphs requires several arrays of figures<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(meaudret)<br />
wit1
134 kplot.sepan<br />
kplot(object, xax = 1, yax = 2, which.tab = 1:length(object$blo),<br />
mfrow = NULL, permute.row.col = FALSE, clab.row = 1,<br />
clab.col = 1.25, csub = 2, possub = "bottomright",<br />
show.eigen.value = TRUE, poseig = c("bottom", "top"), ...)<br />
Arguments<br />
Details<br />
object<br />
xax, yax<br />
which.tab<br />
an object of class sepan<br />
the numbers of the x-axis and the y-axis<br />
a numeric vector containing the numbers of the tables to analyse<br />
mfrow parameter for the array of figures to be drawn, otherwise use n2mfrow<br />
permute.row.col<br />
if TRUE the rows are represented by arrows and the columns by points, if<br />
FALSE it is the opposite<br />
clab.row<br />
clab.col<br />
traject.row<br />
csub<br />
a character size for the row labels<br />
a character size for the column labels<br />
a logical value indicating whether the trajectories between rows should be drawn<br />
in a natural order<br />
a character size for the sub-titles, used with par("cex")*csub<br />
possub a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
show.eigen.value<br />
a logical value indicating whether the eigenvalues bar plot should be drawn<br />
poseig<br />
if "top" the eigenvalues bar plot is upside, if "bottom", it is downside<br />
... further arguments passed to or from other methods<br />
kplot.sepan superimposes the points for the rows and the arrows for the columns using an<br />
adapted rescaling such as the scatter.dudi.<br />
kplot.sepan.coa superimposes the row coordinates and the column coordinates with the same<br />
scale.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(escopage)<br />
w
kplot.statis 135<br />
w
136 krandtest<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(jv73)<br />
dudi1
ktab 137<br />
Value<br />
plot.krandtest draws the p simulated values histograms and the position of the observed<br />
value.<br />
Author(s)<br />
Daniel Chessel and Stephane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
See Also<br />
randtest<br />
Examples<br />
wkrandtest
138 ktab<br />
Usage<br />
## S3 method for class 'ktab':<br />
c(...)<br />
## S3 method for class 'ktab':<br />
x[selection]<br />
is.ktab(x)<br />
## S3 method for class 'ktab':<br />
t(x)<br />
## S3 method for class 'ktab':<br />
row.names(x)<br />
## S3 method for class 'ktab':<br />
col.names(x)<br />
tab.names(x)<br />
col.names(x)<br />
ktab.util.names(x)<br />
Arguments<br />
x<br />
an object of the class ktab<br />
... a sequence of objects of the class ktab<br />
selection an integer vector<br />
Details<br />
A ’ktab’ object can be created with :<br />
a list of data frame : ktab.list.df<br />
a list of dudi objects : ktab.list.dudi<br />
a data.frame : ktab.data.frame<br />
an object within : ktab.within<br />
a couple of ktabs : ktab.match2ktabs<br />
Value<br />
c.ktab returns an object ktab. It concatenates K-tables with the same rows in common.<br />
t.ktab returns an object ktab. It permutes each data frame into a K-tables. All tables have the<br />
same column names and the same column weightings (a data cube).<br />
"[" returns an object ktab. It allows to select some arrays in a K-tables.<br />
is.ktab returns TRUE if x is a K-tables.<br />
row.names returns the vector of the row names common with all the tables of a K-tables and<br />
allowes to modifie them.<br />
col.names returns the vector of the column names of a K-tables and allowes to modifie them.<br />
tab.names returns the vector of the array names of a K-tables and allowes to modifie them.<br />
ktab.util.names is a useful function.<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉
ktab.data.frame 139<br />
Examples<br />
data(friday87)<br />
wfri
140 ktab.list.df<br />
Examples<br />
data(escopage)<br />
wescopage
ktab.list.dudi 141<br />
Examples<br />
data(jv73)<br />
l0
142 ktab.match2ktabs<br />
ll
ktab.within 143<br />
Examples<br />
data(meau)<br />
wit1
144 lascaux<br />
Examples<br />
data(bacteria)<br />
w1
lingoes 145<br />
Examples<br />
data(lascaux)<br />
par(mfrow = c(2,2))<br />
barplot(dudi.pca(lascaux$meris, scan = FALSE)$eig)<br />
title(main = "Meristic")<br />
barplot(dudi.pca(lascaux$colo, scan = FALSE)$eig)<br />
title(main = "Coloration")<br />
barplot(dudi.pca(na.omit(lascaux$morpho), scan = FALSE)$eig)<br />
title(main = "Morphometric")<br />
barplot(dudi.acm(na.omit(lascaux$orne), scan = FALSE)$eig)<br />
title(main = "Ornemental")<br />
par(mfrow = c(1,1))<br />
lingoes<br />
Transformation of a Distance Matrix for becoming Euclidean<br />
Description<br />
transforms a distance matrix in a Euclidean one.<br />
Usage<br />
lingoes(distmat, print = FALSE)<br />
Arguments<br />
distmat<br />
print<br />
an object of class dist<br />
if TRUE, prints the eigenvalues of the matrix<br />
Details<br />
<strong>The</strong> function uses the smaller positive constant k which transforms the matrix of<br />
an Euclidean one<br />
√<br />
d 2 ij + 2 ∗ k in<br />
Value<br />
returns an object of class dist with a Euclidean distance<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Lingoes, J.C. (1971) Some boundary conditions for a monotone analysis of symmetric matrices.<br />
Psychometrika, 36, 195–203.
146 lizards<br />
Examples<br />
data(capitales)<br />
d0
macaca 147<br />
References<br />
Bauwens, D., and Díaz-Uriarte, R. (1997) Covariation of life-history traits in lacertid lizards: a<br />
comparative study. American Naturalist, 149, 91–111.<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps063.pdf (in French).<br />
Examples<br />
data(lizards)<br />
w
148 mafragh<br />
pro2
mantel.randtest 149<br />
<strong>Source</strong><br />
Belair, G.d. and Bencheikh-Lehocine, M. (1987) Composition et déterminisme de la végétation<br />
d’une plaine côtière marécageuse : La Mafragh (Annaba, Algérie). Bulletin d’Ecologie, 18, 393–<br />
407.<br />
References<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps053.pdf (in French).<br />
Examples<br />
data(mafragh)<br />
par(mfrow = c(3,2))<br />
s.label(mafragh$xy, inc = FALSE, neig = mafragh$neig,<br />
sub = "Samples & Neighbourhood graph")<br />
coa1
150 mantel.rtest<br />
Description<br />
Performs a Mantel test between two distance matrices.<br />
Usage<br />
mantel.randtest(m1, m2, nrepet = 999)<br />
Arguments<br />
m1<br />
m2<br />
nrepet<br />
an object of class dist<br />
an object of class dist<br />
the number of permutations<br />
Value<br />
an object of class randtest (randomization tests)<br />
Author(s)<br />
Jean Thioulouse 〈<strong>ade4</strong>-jt@biomserv.univ-lyon1.fr〉<br />
References<br />
Mantel, N. (1967) <strong>The</strong> detection of disease clustering and a generalized regression approach. Cancer<br />
Research, 27, 209–220.<br />
Examples<br />
data(yanomama)<br />
gen
maples 151<br />
Arguments<br />
m1<br />
m2<br />
nrepet<br />
an object of class dist<br />
an object of class dist<br />
the number of permutations<br />
Value<br />
an object of class rtest (randomization tests)<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Mantel, N. (1967) <strong>The</strong> detection of disease clustering and a generalized regression approach. Cancer<br />
Research, 27, 209–220.<br />
Examples<br />
data(yanomama)<br />
gen
152 mariages<br />
<strong>Source</strong><br />
Data were obtained from the URL http://www.stanford.edu/~dackerly/acerdata.<br />
html.<br />
References<br />
Ackerly, D. D. and Donoghue, M.J. (1998) Leaf size, sappling allometry, and Corner’s rules: phylogeny<br />
and correlated evolution in Maples (Acer). American Naturalist, 152, 767–791.<br />
Examples<br />
data(maples)<br />
phy
mcoa 153<br />
<strong>Source</strong><br />
Codes for rows and columns are identical : agri (Farmers), ouva (Farm workers), pat (Company directors<br />
(commerce and industry)), sup (Liberal profession, executives and higher intellectual professions),<br />
moy (Intermediate professions), emp (Other white-collar workers), ouv (Manual workers),<br />
serv (Domestic staff), aut (other workers).<br />
Vallet, L.A. (1986) Activité professionnelle de la femme mariée et détermination de la position<br />
sociale de la famille. Un test empirique : la France entre 1962 et 1982. Revue Française de<br />
Sociologie, 27, 656–696.<br />
Examples<br />
data(mariages)<br />
par(mfrow = c(2,2))<br />
w
154 mcoa<br />
"internal"<br />
scannf<br />
nf<br />
tol<br />
weighting included in X$tabw<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
a tolerance threshold, an eigenvalue is considered positive if it is larger than<br />
-tol*lambda1 where lambda1 is the largest eigenvalue.<br />
x, object an object of class ’mcoa’<br />
... further arguments passed to or from other methods<br />
xax, yax<br />
eig.bottom<br />
the numbers of the x-axis and the y-axis<br />
a logical value indicating whether the eigenvalues bar plot should be added<br />
Value<br />
mcoa returns a list of class ’mcoa’ containing :<br />
pseudoeig<br />
call<br />
nf<br />
SynVar<br />
axis<br />
Tli<br />
Tl1<br />
Tax<br />
Tco<br />
TL<br />
TC<br />
T4<br />
lambda<br />
cov2<br />
a numeric vector with the all pseudo eigenvalues<br />
the call-up order<br />
a numeric value indicating the number of kept axes<br />
a data frame with the synthetic scores<br />
a data frame with the co-inertia axes<br />
a data frame with the co-inertia coordinates<br />
a data frame with the co-inertia normed scores<br />
a data frame with the inertia axes onto co-inertia axis<br />
a data frame with the column coordinates onto synthetic scores<br />
a data frame with the factors for Tli Tl1<br />
a data frame with the factors for Tco<br />
a data frame with the factors for Tax<br />
a data frame with the all eigenvalues (computed on the separate analyses)<br />
a numeric vector with the all pseudo eigenvalues (synthetic analysis)<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Chessel, D. and Hanafi, M. (1996) Analyses de la co-inertie de K nuages de points, Revue de<br />
Statistique Appliquée, 44, 35–60.
meau 155<br />
Examples<br />
data(friday87)<br />
w1
156 meaudret<br />
meaudret<br />
Ecological Data : sites-variables, sites-species, where and when<br />
Description<br />
This data set contains information about sites, environmental variables and species (Trichopters).<br />
Usage<br />
data(meaudret)<br />
Format<br />
meaudret is a list of 3 components.<br />
mil is a data frame with 20 sites and 9 variables.<br />
fau is a data frame with 20 sites and 13 species (Trichopters).<br />
plan is a data frame with 20 sites and 2 factors.<br />
dat is a factor with 4 levels.<br />
sta is a factor with 5 levels.<br />
<strong>Source</strong><br />
Pegaz-Maucet, D. (1980) Impact d’une perturbation d’origine organique sur la dérive des macroinvertébérés<br />
benthiques d’un cours d’eau. Comparaison avec le benthos. Thèse de troisième cycle,<br />
Université Lyon 1, 130 p.<br />
Examples<br />
data(meaudret)<br />
par(mfrow = c(2,2))<br />
pca1
mfa 157<br />
mfa<br />
Multiple Factorial Analysis<br />
Description<br />
Usage<br />
performs a multiple factorial analysis, using an object of class ktab.<br />
mfa(X, option = c("lambda1", "inertia", "uniform", "internal"),<br />
scannf = TRUE, nf = 3)<br />
## S3 method for class 'mfa':<br />
plot(x, xax = 1, yax = 2, option.plot = 1:4, ...)<br />
## S3 method for class 'mfa':<br />
print(x, ...)<br />
## S3 method for class 'mfa':<br />
summary(object, ...)<br />
Arguments<br />
X<br />
K-tables, an object of class ktab<br />
option a string of characters for the weighting of arrays options :<br />
lambda1<br />
inertia<br />
uniform<br />
internal<br />
scannf<br />
nf<br />
Value<br />
weighting of group k by the inverse of the first eigenvalue of the k analysis<br />
weighting of group k by the inverse of the total inertia of the array k<br />
uniform weighting of groups<br />
weighting included in X$tabw<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
x, object an object of class ’mfa’<br />
xax, yax<br />
option.plot<br />
the numbers of the x-axis and the y-axis<br />
an integer between 1 and 4, otherwise the 4 components of the plot are displayed<br />
... further arguments passed to or from other methods<br />
Returns a list including :<br />
tab<br />
rank<br />
eig<br />
li<br />
TL<br />
a data frame with the modified array<br />
a vector of ranks for the analyses<br />
a numeric vector with the all eigenvalues<br />
a data frame with the coordinates of rows<br />
a data frame with the factors associated to the rows (indicators of table)
158 microsatt<br />
co<br />
TC<br />
blo<br />
lisup<br />
cg<br />
link<br />
corli<br />
a data frame with the coordinates of columns<br />
a data frame with the factors associated to the columns (indicators of table)<br />
a vector indicating the number of variables for each table<br />
a data frame with the projections of normalized scores of rows for each table<br />
a data frame with the gravity center for the lisup<br />
a data frame containing the projected inertia and the links between the arrays<br />
and the reference array<br />
a data frame giving the correlations between the $lisup and the $li<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Escofier, B. and Pagès, J. (1994) Multiple factor analysis (AFMULT package), Computational<br />
Statistics and Data Analysis, 18, 121–140.<br />
Examples<br />
data(friday87)<br />
w1
microsatt 159<br />
Format<br />
microsatt is a list of 4 components.<br />
tab contains the allelic frequencies for 18 cattle breeds (Taurine or Zebu,French or African) and 9<br />
microsatellites.<br />
loci.names is a vector of the names of loci.<br />
loci.eff is a vector of the number of alleles per locus.<br />
alleles.names is a vector of the names of alleles.<br />
<strong>Source</strong><br />
Extract of data prepared by D. Laloë 〈ugendla@dga2.jouy.inra.fr〉 from data used in:<br />
Moazami-Goudarzi, K., D. Laloë, J. P. Furet, and F. Grosclaude (1997) Analysis of genetic relationships<br />
between 10 cattle breeds with 17 microsatellites. Animal Genetics, 28, 338–345.<br />
Souvenir Zafindrajaona, P.,Zeuh V. ,Moazami-Goudarzi K., Laloë D., Bourzat D., Idriss A., and<br />
Grosclaude F. (1999) Etude du statut phylogénétique du bovin Kouri du lac Tchad à l’aide de marqueurs<br />
moléculaires. Revue d’Elevage et de Médecine Vétérinaire des pays Tropicaux, 55, 155–162.<br />
Moazami-Goudarzi, K., Belemsaga D. M. A., Ceriotti G., Laloë D. , Fagbohoun F., Kouagou N. T.,<br />
Sidibé I., Codjia V., Crimella M. C., Grosclaude F. and Touré S. M. (2001)<br />
Caractérisation de la race bovine Somba à l’aide de marqueurs moléculaires. Revue d’Elevage et de<br />
Médecine Vétérinaire des pays Tropicaux, 54, 1–10.<br />
References<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps055.pdf (in French).<br />
Examples<br />
## Not run:<br />
data(microsatt)<br />
fac
160 mjrochet<br />
mjrochet<br />
Phylogeny and quantitative traits of teleos fishes<br />
Description<br />
This data set describes the phylogeny of 49 teleos fishes as reported by Rochet et al. (2000). It also<br />
gives life-history traits corresponding to these 49 species.<br />
Usage<br />
data(mjrochet)<br />
Format<br />
mjrochet is a list containing the 2 following objects :<br />
tre is a character string giving the phylogenetic tree in Newick format.<br />
tab is a data frame with 49 rows and 7 traits.<br />
Details<br />
Variables of mjrochet$tab are the following ones : tm (age at maturity (years)), lm (length at<br />
maturity (cm)), l05 (length at 5 per cent survival (cm)), t05 (time to 5 per cent survival (years)),<br />
fb (slope of the log-log fecundity-length relationship), fm (fecundity the year of maturity), egg<br />
(volume of eggs (mm 3 )).<br />
<strong>Source</strong><br />
Data taken from:<br />
Summary of data - Clupeiformes : http://www.ifremer.fr/maerha/clupe.html<br />
Summary of data - Argentiniformes : http://www.ifremer.fr/maerha/argentin.html<br />
Summary of data - Salmoniformes : http://www.ifremer.fr/maerha/salmon.html<br />
Summary of data - Gadiformes : http://www.ifremer.fr/maerha/gadi.html<br />
Summary of data - Lophiiformes : http://www.ifremer.fr/maerha/loph.html<br />
Summary of data - Atheriniformes : http://www.ifremer.fr/maerha/ather.html<br />
Summary of data - Perciformes : http://www.ifremer.fr/maerha/perci.html<br />
Summary of data - Pleuronectiformes : http://www.ifremer.fr/maerha/pleuro.html<br />
Summary of data - Scorpaeniformes : http://www.ifremer.fr/maerha/scorpa.html<br />
Phylogenetic tree : http://www.ifremer.fr/maerha/life_history.html<br />
References<br />
Rochet, M. J., Cornillon, P-A., Sabatier, R. and Pontier, D. (2000) Comparative analysis of phylogenic<br />
and fishing effects in life history patterns of teleos fishes. Oïkos, 91, 255–270.
mld 161<br />
Examples<br />
data(mjrochet)<br />
mjrochet.phy
162 mollusc<br />
References<br />
Mallat, S. G. (1989) A theory for multiresolution signal decomposition: the wavelet representation.<br />
IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 7, 674–693.<br />
Percival, D. B. and Walden, A. T. (2000) Wavelet Methods for Time Series Analysis, Cambridge<br />
University Press.<br />
See Also<br />
gridrowcol, orthobasis, orthogram, mra for multiresolution analysis with various families<br />
of wavelets<br />
Examples<br />
## Not run:<br />
# decomposition of a time serie<br />
data(co2)<br />
x
monde84 163<br />
Format<br />
<strong>Source</strong><br />
mollusc is a list of 2 objects.<br />
fau is a data frame with 163 samples and 32 mollusk species (abundance).<br />
plan contains the 163 samples and 4 variables.<br />
Richardot-Coulet, M., Chessel D. and Bournaud M. (1986) Typological value of the benthos of old<br />
beds of a large river. Methodological approach. Archiv fùr Hydrobiologie, 107, 363–383.<br />
Examples<br />
data(mollusc)<br />
coa1
164 morphosport<br />
Examples<br />
data(monde84)<br />
X
mstree 165<br />
mstree<br />
Minimal Spanning Tree<br />
Description<br />
Minimal Spanning Tree<br />
Usage<br />
mstree(xdist, ngmax = 1)<br />
Arguments<br />
xdist<br />
ngmax<br />
an object of class dist containing an observed dissimilarity<br />
a component number (default=1). Select 1 for getting classical MST. To add n<br />
supplementary edges k times: select k+1.<br />
Value<br />
returns an object of class neig<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(mafragh)<br />
maf.coa = dudi.coa(mafragh$flo, scan = FALSE)<br />
maf.mst = mstree(dist.dudi(maf.coa), 1)<br />
s.label(maf.coa$li, clab = 0, cpoi = 2, neig = maf.mst, cnei = 1)<br />
xy = data.frame(x = runif(20), y = runif(20))<br />
par(mfrow = c(2,2))<br />
for (k in 1:4) {<br />
neig = mstree (dist.quant(xy,1), k)<br />
s.label(xy, xlim = c(0,1), ylim = c(0,1), addax = FALSE, neig = neig)<br />
}
166 multispati<br />
multispati<br />
Multivariate spatial analysis<br />
Description<br />
This function ensures a multivariate extension of the univariate method of spatial autocorrelation<br />
analysis. By accounting for the spatial dependence of data observations and their multivariate<br />
covariance simultaneously, complex interactions among many variables are analysed. Using<br />
a methodological scheme borrowed from duality diagram analysis, a strategy for the exploratory<br />
analysis of spatial pattern in the multivariate is developped.<br />
Usage<br />
multispati(dudi, listw, scannf = TRUE, nfposi = 2, nfnega = 0)<br />
## S3 method for class 'multispati':<br />
plot(x, xax = 1, yax = 2, ...)<br />
## S3 method for class 'multispati':<br />
summary(object, ...)<br />
## S3 method for class 'multispati':<br />
print(x, ...)<br />
Arguments<br />
Details<br />
dudi<br />
listw<br />
scannf<br />
nfposi<br />
nfnega<br />
an object of class dudi for the duality diagram analysis<br />
an object of class listw for the spatial dependence of data observations<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
an integer indicating the number of kept positive axes<br />
an integer indicating the number of kept negative axes<br />
x, object an object of class multispati<br />
xax, yax<br />
the numbers of the x-axis and the y-axis<br />
... further arguments passed to or from other methods<br />
This analysis generalizes the Wartenberg’s multivariate spatial correlation analysis to various duality<br />
diagrams created by the functions (dudi.pca, dudi.coa, dudi.acm, dudi.mix...) If dudi<br />
is a duality diagram created by the function dudi.pca and listw gives spatial weights created by<br />
a row normalized coding scheme, the analysis is equivalent to Wartenberg’s analysis.<br />
We note X the data frame with the variables, Q the column weights matrix and D the row weights<br />
matrix associated to the duality diagram dudi. We note L the neighbouring weights matrix associated<br />
to listw. <strong>The</strong>n, the ’multispati’ analysis gives principal axes v that maximize the product<br />
of spatial autocorrelation and inertia of row scores :<br />
I(XQv) ∗ ‖XQv‖ 2 = v t Q t X t DLXQv
multispati 167<br />
Value<br />
Returns an object of class multispati, which contains the following elements :<br />
eig<br />
nfposi<br />
nfnega<br />
c1<br />
li<br />
a numeric vector containing the eigenvalues<br />
integer, number of kept axes associated to positive eigenvalues<br />
integer, number of kept axes associated to negative eigenvalues<br />
principle axes (v), data frame with p rows and (nfposi + nfnega) columns<br />
principal components (XQv), data frame with n rows and (nfposi + nfnega)<br />
columns<br />
ls lag vector onto the principal axes (LXQv), data frame with n rows and (nfposi +<br />
nfnega) columns<br />
as<br />
Author(s)<br />
principal axes of the dudi analysis (u) onto principal axes of multispati (t(u)Qv),<br />
data frame with dudi$nf rows and (nfposi + nfnega) columns<br />
Daniel Chessel<br />
Sebastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
Thibaut Jombart 〈jombart@biomserv.univ-lyon1.fr〉<br />
References<br />
Grunsky, E. C. and Agterberg, F. P. (1988) Spatial and multivariate analysis of geochemical data<br />
from metavolcanic rocks in the Ben Nevis area, Ontario. Mathematical Geology, 20, 825–861.<br />
Switzer, P. and Green, A.A. (1984) Min/max autocorrelation factors for multivariate spatial imagery.<br />
Tech. rep. 6, Stanford University.<br />
Thioulouse, J., Chessel, D. and Champely, S. (1995) Multivariate analysis of spatial patterns: a<br />
unified approach to local and global structures. Environmental and Ecological Statistics, 2, 1–14.<br />
Wartenberg, D. E. (1985) Multivariate spatial correlation: a method for exploratory geographical<br />
analysis. Geographical Analysis, 17, 263–283.<br />
Jombart, T., Devillard, S., Dufour, A.-B. and Pontier, D. A spatially explicit multivariate method to<br />
disentangle global and local patterns of genetic variability. Submitted to Genetics.<br />
See Also<br />
dudi,listw<br />
Examples<br />
## Not run:<br />
if (require(maptools, quiet = TRUE) & require(spdep, quiet = TRUE)) {<br />
data(mafragh)<br />
maf.xy
168 multispati<br />
maf.coa.ms
multispati.randtest 169<br />
w1.msm
170 multispati.rtest<br />
References<br />
Smouse, P. E. and Peakall, R. (1999) Spatial autocorrelation analysis of individual multiallele and<br />
multilocus genetic structure. Heredity, 82, 561–573.<br />
See Also<br />
dudi,listw<br />
Examples<br />
if (require(maptools, quiet = TRUE) & require(spdep, quiet = TRUE)) {<br />
data(mafragh)<br />
maf.listw
neig 171<br />
Author(s)<br />
Daniel Chessel<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
References<br />
Smouse, P. E. and Peakall, R. (1999) Spatial autocorrelation analysis of individual multiallele and<br />
multilocus genetic structure. Heredity, 82, 561–573.<br />
See Also<br />
dudi,listw<br />
Examples<br />
if (require(maptools, quiet = TRUE) & require(spdep, quiet = TRUE)) {<br />
data(mafragh)<br />
maf.listw
172 neig<br />
Usage<br />
neig(list = NULL, mat01 = NULL, edges = NULL,<br />
n.line = NULL, n.circle = NULL, area = NULL)<br />
scores.neig (obj)<br />
## S3 method for class 'neig':<br />
print(x, ...)<br />
## S3 method for class 'neig':<br />
summary(object, ...)<br />
nb2neig (nb)<br />
neig2nb (neig)<br />
neig2mat (neig)<br />
Arguments<br />
list<br />
mat01<br />
edges<br />
n.line<br />
n.circle<br />
area<br />
a list which each component gives the number of neighbours<br />
a symmetric square matrix of 0-1 values<br />
a matrix of 2 columns with integer values giving a list of edges<br />
the number of points for a linear plot<br />
the number of points for a circular plot<br />
a data frame containing a polygon set (see area.plot)<br />
nb<br />
an object of class ’nb’<br />
neig, x, obj, object<br />
an object of class ’neig’<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
References<br />
Thioulouse, J., D. Chessel, and S. Champely. 1995. Multivariate analysis of spatial patterns: a<br />
unified approach to local and global structures. Environmental and Ecological Statistics, 2, 1–14.<br />
Examples<br />
data(mafragh)<br />
if (require(tripack, quietly=TRUE)) {<br />
par(mfrow = c(2,1))<br />
provi
neig 173<br />
#hist(dist, nclass = 50)<br />
mafragh.neig
174 newick.eg<br />
w
newick2phylog 175<br />
References<br />
Bauwens, D. and Díaz-Uriarte, R. (1997) Covariation of life-history traits in lacertid lizards: a<br />
comparative study. American Naturalist, 149, 91–111.<br />
Cheverud, J. and Dow, M.M. (1985) An autocorrelation analysis of genetic variation due to lineal<br />
fission in social groups of rhesus macaques. American Journal of Physical Anthropology, 67, 113–<br />
122.<br />
Martins, E. P. and Hansen, T.F. (1997) Phylogenies and the comparative method: a general approach<br />
to incorporating phylogenetic information into the analysis of interspecific data. American<br />
Naturalist, 149, 646–667.<br />
Examples<br />
data(newick.eg)<br />
newick2phylog(newick.eg[[11]])<br />
radial.phylog(newick2phylog(newick.eg[[7]]), circ = 1,<br />
clabel.l = 0.75)<br />
newick2phylog<br />
Create phylogeny<br />
Description<br />
Usage<br />
<strong>The</strong> first three functions ensure to create object of class phylog from either a character string in<br />
Newick format (newick2phylog) or an object of class ’hclust’ (hclust2phylog) or a<br />
taxonomy (taxo2phylog). <strong>The</strong> function newick2phylog.addtools is an internal function<br />
called by newick2phylog, hclust2phylog and taxo2phylog when newick2phylog.addtools<br />
= TRUE. It adds some items in ’phylog’ objects.<br />
newick2phylog(x.tre, add.tools = TRUE, call = match.call())<br />
hclust2phylog(hc, add.tools = TRUE)<br />
taxo2phylog(taxo, add.tools = FALSE, root="Root", abbrev=TRUE)<br />
newick2phylog.addtools(res, tol = 1e-07)<br />
Arguments<br />
x.tre<br />
add.tools<br />
call<br />
hc<br />
taxo<br />
res<br />
a character string corresponding to a phylogenetic tree in Newick format<br />
(http://evolution.genetics.washington.edu/phylip/newicktree.<br />
html)<br />
if TRUE, executes the function newick2phylog.addtools<br />
call<br />
an object of class hclust<br />
an object of class taxo<br />
an object of class phylog (an internal argument of the function newick2phylog)
176 newick2phylog<br />
tol<br />
root<br />
abbrev<br />
used in case 3 of method as a tolerance threshold for null eigenvalues<br />
a character string for the root of the tree<br />
logical : if TRUE levels are abbreviated by column and two characters are added<br />
before<br />
Value<br />
Return object of class phylog.<br />
Author(s)<br />
Daniel Chessel<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
See Also<br />
phylog, plot.phylog, as.taxo<br />
Examples<br />
w
niche 177<br />
w[19]
178 niche<br />
Description<br />
Usage<br />
performs a special multivariate analysis for ecological data.<br />
niche(dudiX, Y, scannf = TRUE, nf = 2)<br />
## S3 method for class 'niche':<br />
print(x, ...)<br />
## S3 method for class 'niche':<br />
plot(x, xax = 1, yax = 2, ...)<br />
niche.param(x)<br />
## S3 method for class 'niche':<br />
rtest(xtest,nrepet=99, ...)<br />
Arguments<br />
dudiX<br />
Y<br />
scannf<br />
nf<br />
x<br />
Value<br />
a duality diagram providing from a function dudi.coa, dudi.pca, ... using<br />
an array sites-variables<br />
a data frame sites-species according to dudiX$tab with no columns of zero<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
an object of class niche<br />
... further arguments passed to or from other methods<br />
xax, yax<br />
xtest<br />
nrepet<br />
the numbers of the x-axis and the y-axis<br />
an object of class niche<br />
the number of permutations for the testing procedure<br />
Returns a list of the class niche (sub-class of dudi) containing :<br />
rank<br />
nf<br />
RV<br />
eig<br />
lw<br />
tab<br />
li<br />
l1<br />
co<br />
c1<br />
ls<br />
as<br />
an integer indicating the rank of the studied matrix<br />
an integer indicating the number of kept axes<br />
a numeric value indicating the RV coefficient<br />
a numeric vector with the all eigenvalues<br />
a data frame with the row weigths (crossed array)<br />
a data frame with the crossed array (averaging species/sites)<br />
a data frame with the species coordinates<br />
a data frame with the species normed scores<br />
a data frame with the variable coordinates<br />
a data frame with the variable normed scores<br />
a data frame with the site coordinates<br />
a data frame with the axis upon niche axis
njplot 179<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
Stephane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Dolédec, S., Chessel, D. and Gimaret, C. (2000) Niche separation in community analysis: a new<br />
method. Ecology, 81, 2914–1927.<br />
Examples<br />
data(doubs)<br />
dudi1
180 olympic<br />
Usage<br />
data(njplot)<br />
Format<br />
njplot is a list containing the 2 following objects:<br />
tre is a character string giving the fission tree in Newick format.<br />
tauxcg is a numeric vector that gives the CG rate of the 36 species.<br />
<strong>Source</strong><br />
Data were obtained by Manolo Gouy 〈mgouy@biomserv.univ-lyon1.fr〉<br />
References<br />
Perrière, G. and Gouy, M. (1996) WWW-Query : an on-line retrieval system for biological sequence<br />
banks. Biochimie, 78, 364–369.<br />
Examples<br />
data(njplot)<br />
njplot.phy
optimEH 181<br />
<strong>Source</strong><br />
Example 357 in:<br />
Hand, D.J., Daly, F., Lunn, A.D., McConway, K.J. and Ostrowski, E. (1994) A handbook of small<br />
data sets, Chapman & Hall, London. 458 p.<br />
Lunn, A. D. and McNeil, D.R. (1991) Computer-Interactive Data Analysis, Wiley, New York<br />
Examples<br />
data(olympic)<br />
pca1
182 oribatid<br />
Value<br />
Returns a list containing:<br />
value<br />
selected.sp<br />
a real value providing the amount of evolutionary history preserved.<br />
a data frame containing the list of the k species which optimize the amount of<br />
evolutionary history preserved and are the most original species in their clades.<br />
Author(s)<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉<br />
References<br />
Nee, S. and May, R.M. (1997) Extinction and the loss of evolutionary history. Science 278, 692–<br />
694.<br />
Pavoine, S., Ollier, S. and Dufour, A.-B. (2005) Is the originality of a species measurable? Ecology<br />
Letters, 8, 579–586.<br />
See Also<br />
randEH<br />
Examples<br />
data(carni70)<br />
carni70.phy
originality 183<br />
Details<br />
Variables of oribatid$envir are the following ones :<br />
substrate: a factor with seven levels that describes the nature of the substratum<br />
shrubs: a factor with three levels that describes the absence/presence of shrubs<br />
topo: a factor with two levels that describes the microtopography<br />
density: substratum density (g.L −1 )<br />
water: water content of the substratum (g.L −1 )<br />
<strong>Source</strong><br />
Data prepared by P. Legendre 〈Pierre.Legendre@umontreal.ca〉 and<br />
D. Borcard 〈borcardd@magellan.umontreal.ca〉 starting from<br />
http://www.fas.umontreal.ca/biol/casgrain/fr/labo/oribates.html<br />
References<br />
Borcard, D., and Legendre, P. (1994) Environmental control and spatial structure in ecological<br />
communities: an example using Oribatid mites (Acari Oribatei). Environmental and Ecological<br />
Statistics, 1, 37–61.<br />
Borcard, D., Legendre, P., and Drapeau, P. (1992) Partialling out the spatial component of ecological<br />
variation. Ecology, 73, 1045–1055.<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps039.pdf (in French).<br />
Examples<br />
data(oribatid)<br />
ori.xy
184 originality<br />
Usage<br />
originality(phyl, method = 5)<br />
Arguments<br />
phyl<br />
an object of class phylog<br />
method a vector containing integers between 1 and 5.<br />
Details<br />
1 = Vane-Wright et al.’s (1991) node-counting index 2 = May’s (1990) branch-counting index 3<br />
= Nixon and Wheeler’s (1991) unweighted index, based on the sum of units in binary values 4 =<br />
Nixon and Wheeler’s (1991) weighted index 5 = QE-based index<br />
Value<br />
Returns a data frame with species in rows, and the selected indices of originality in columns. Indices<br />
are expressed as percentages.<br />
Author(s)<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉<br />
References<br />
Pavoine, S., Ollier, S. and Dufour, A.-B. (2005) Is the originality of a species measurable? Ecology<br />
Letters, 8, 579–586.<br />
Vane-Wright, R.I., Humphries, C.J. and Williams, P.H. (1991). What to protect? Systematics and<br />
the agony of choice. Biological Conservation, 55, 235–254.<br />
May, R.M. (1990). Taxonomy as destiny. Nature, 347, 129–130.<br />
Nixon, K.C. & Wheeler, Q.D. (1992). Measures of phylogenetic diversity. In: Extinction and<br />
Phylogeny (eds. Novacek, M.J. and Wheeler, Q.D.), 216–234, Columbia University Press, New<br />
York.<br />
Examples<br />
data(carni70)<br />
carni70.phy
orisaved 185<br />
orisaved<br />
Maximal or minimal amount of originality saved under optimal conditions<br />
Description<br />
computes the maximal or minimal amount of originality saved over all combinations of species<br />
optimizing the amount of evolutionary history preserved. <strong>The</strong> originality of a species is measured<br />
with the QE-based index.<br />
Usage<br />
orisaved(phyl, rate = 0.1, method = 1)<br />
Arguments<br />
phyl<br />
rate<br />
method<br />
an object of class phylog<br />
a real value (between 0 and 1) indicating how many species will be saved for<br />
each calculation. For example, if the total number of species is 70 and ’rate =<br />
0.1’ then the calculations will be done at a rate of 10 % i.e. for 0 (= 0 %), 7<br />
(= 10 %), 14 (= 20 %), 21 (= 30 %), ..., 63 (= 90 %) and 70(= 100 %) species<br />
saved. If ’rate = 0.5’ then the calculations will be done for only 0 (= 0 %), 35 (=<br />
50 %) and 70(= 100 %) species saved.<br />
an integer either 1 or 2 (see details).<br />
Details<br />
1 = maximum amount of originality saved 2 = minimum amount of originality saved<br />
Value<br />
Returns a numeric vector.<br />
Author(s)<br />
Sandrine Pavoine 〈pavoine@biomserv.univ-lyon1.fr〉<br />
References<br />
Pavoine, S., Ollier, S. and Dufour, A.-B. (2005) Is the originality of a species measurable? Ecology<br />
Letters, 8, 579–586.
186 orthobasis<br />
Examples<br />
data(carni70)<br />
carni70.phy
orthobasis 187<br />
Value<br />
All the functions excepted print.ortobasis return an object of class orthobasis containing<br />
a data frame. This data frame defines an orthonormal basis with n-1 vectors of length n. Various<br />
attributes are associated to it :<br />
names<br />
row.names<br />
class<br />
values<br />
weights<br />
call<br />
: names of the vectors<br />
: row names of the data frame<br />
: class<br />
: row weights (uniform weights)<br />
: numeric values to class vectors according to their quadratic forms (Moran<br />
ones)<br />
: call<br />
Note<br />
the function orthobasis.haar uses function wavelet.filter from package waveslim.<br />
Author(s)<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
Daniel Chessel<br />
References<br />
Misiti, M., Misiti, Y., Oppenheim, G. and Poggi, J.M. (1993) Analyse de signaux classiques par<br />
décomposition en ondelettes. Revue de Statistique Appliquée, 41, 5–32.<br />
Cornillon, P.A. (1998) Prise en compte de proximités en analyse factorielle et comparative. Thèse,<br />
Ecole Nationale Supérieure Agronomique, Montpellier.<br />
See Also<br />
gridrowcol that defines an orthobasis for square grid, phylog that defines an orthobasis for<br />
phylogenetic tree, orthogram and mld<br />
Examples<br />
# a 2D spatial orthobasis<br />
par(mfrow = c(4,4))<br />
w
188 orthobasis<br />
w
orthogram 189<br />
orthogram<br />
Orthonormal decomposition of variance<br />
Description<br />
This function performs the orthonormal decomposition of variance of a quantitative variable on an<br />
orthonormal basis. It also returns the results of five non parametric tests associated to the variance<br />
decomposition. It thus provides tools (graphical displays and test) for analysing phylogenetic,<br />
spatial and temporal pattern of one quantitative variable.<br />
Usage<br />
orthogram(x, orthobas = NULL, neig = NULL, phylog = NULL,<br />
nrepet = 999, posinega = 0, tol = 1e-07, na.action = c("fail",<br />
"mean"), cdot = 1.5, cfont.main = 1.5, lwd = 2, nclass,<br />
high.scores = 0,alter=c("greater", "less", "two-sided"))<br />
Arguments<br />
x<br />
orthobas<br />
neig<br />
phylog<br />
nrepet<br />
posinega<br />
tol<br />
na.action<br />
cdot<br />
cfont.main<br />
lwd<br />
nclass<br />
high.scores<br />
alter<br />
a numeric vector corresponding to the quantitative variable<br />
an object of class ’orthobasis’<br />
an object of class ’neig’<br />
an object of class ’phylog’<br />
an integer giving the number of permutations<br />
a parameter for the ratio test. If posinega > 0, the function computes the ratio<br />
test.<br />
a tolerance threshold for orthonormality condition<br />
if ’fail’ stops the execution of the current expression when z contains any missing<br />
value. If ’mean’ replaces any missing values by mean(z)<br />
a character size for points on the cumulative decomposition display<br />
a character size for titles<br />
a character size for dash lines<br />
a single number giving the number of cells for the histogram<br />
a single number giving the number of vectors to return. If > 0, the function<br />
returns labels of vectors that explains the larger part of variance.<br />
a character string specifying the alternative hypothesis, must be one of "greater"<br />
(default), "less" or "two-sided"
190 orthogram<br />
Details<br />
<strong>The</strong> function computes the variance decomposition of a quantitative vector x on an orthonormal<br />
basis B. <strong>The</strong> variable is normalized given the uniform weight to eliminate problem of scales. It<br />
plots the squared correlations R 2 between x and vectors of B (variance decomposition) and the<br />
cumulated squared correlations SR 2 (cumulative decomposition). <strong>The</strong> function also provides five<br />
non parametric tests to test the existence of autocorrelation. <strong>The</strong> tests derive from the five following<br />
statistics :<br />
R2Max =max(R 2 ). It takes high value when a high part of the variability is explained by one score.<br />
SkR2k = ∑ n−1<br />
i=1 (iR2 i ). It compares the part of variance explained by internal nodes to the one explained<br />
by end nodes.<br />
Dmax =max m=1,...,n−1 ( ∑ m<br />
scores.<br />
j=1 R2 j − m<br />
n−1<br />
). It examines the accumulation of variance for a sequence of<br />
SCE = ∑ n−1<br />
m=1 (∑ m<br />
j=1 R2 j − m<br />
n−1 )2 . It examines also the accumulation of variance for a sequence of scores.<br />
ratio depends of the parameter posinega. If posinega > 0, the statistic ratio exists and equals ∑ posinega<br />
i=1<br />
R 2 i .<br />
It compares the part of variance explained by internal nodes to the one explained by end nodes when<br />
we can define how many vectors correspond to internal nodes.<br />
Value<br />
If (high.scores = 0), returns an object of class ’krandtest’ (randomization tests) corresponding<br />
to the five non parametric tests.<br />
If (high.scores > 0), returns a list containg :<br />
w<br />
: an object of class ’krandtest’ (randomization tests)<br />
scores.order : a vector which terms give labels of vectors that explain the larger part of variance<br />
Author(s)<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
Daniel Chessel<br />
References<br />
Ollier, S., Chessel, D. and Couteron, P. (2005) Orthonormal Transform to Decompose the Variance<br />
of a Life-History Trait across a Phylogenetic Tree. Biometrics, 62, 471–477.<br />
See Also<br />
gridrowcol, orthobasis, mld
ours 191<br />
Examples<br />
# a phylogenetic example<br />
data(ungulates)<br />
ung.phy
192 ours<br />
Usage<br />
data(ours)<br />
Format<br />
This data frame contains the following columns:<br />
altit importance of the altitudinal area inhabited by bears, a factor with levels: 1 less than 50% of<br />
the area between 800 and 2000 meters 2 between 50 and 70% 3 more than 70%<br />
deniv importance of the average variation in level by square of 50 km2, a factor with levels: 1 less<br />
than 700m 2 between 700 and 900 m 3 more than 900 m<br />
cloiso partitioning of the massif, a factor with levels: 1 a great valley or a ridge isolates at least a<br />
quarter of the massif 2 less than a quarter of the massif is isolated 3 the massif has no split<br />
domain importance of the national forests on contact with the massif, a factor with levels: 1 less than<br />
400 km2 2 between 400 and 1000 km2 3 more than 1000 km2<br />
boise rate of afforestation, a factor with levels: 1 less than 30% 2 between 30 and 50% 3 more than<br />
50%<br />
hetra importance of plantations and mixed forests, a factor with levels: 1 less than 5% 2 between 5<br />
and 10% 3 more than 10% of the massif<br />
favor importance of favorable forests, plantations, mixed forests, fir plantations, a factor with levels:<br />
1 less than 5% 2 between 5 and 10% 3 more than 10% of the massif<br />
inexp importance of unworked forests, a factor with levels: 1 less than 4% 2 between 4 and 8% 3<br />
more than 8% of the total area<br />
citat presence of the bear before its disappearance, a factor with levels: 1 no quotation since 1840<br />
2 1 to 3 quotations before 1900 and none after 3 4 quotations before 1900 and none after 4 at<br />
least 4 quotations before 1900 and at least 1 quotation between 1900 and 1940<br />
depart district, a factor with levels: AHP Alpes-de-Haute-Provence AM Alpes-Maritimes D Drôme HP<br />
Hautes-Alpes HS Haute-Savoie I Is"re S Savoie<br />
<strong>Source</strong><br />
Erome, G. (1989) L’ours brun dans les Alpes françaises. Historique de sa disparition. Centre<br />
Ornithologique Rhône-Alpes, Villeurbanne. 120 p.<br />
Examples<br />
data(ours)<br />
boxplot(dudi.acm(ours, scan = FALSE))
palm 193<br />
palm<br />
Phylogenetic and quantitative traits of amazonian palm trees<br />
Description<br />
Usage<br />
Format<br />
Details<br />
This data set describes the phylogeny of 66 amazonian palm trees. It also gives 7 traits corresponding<br />
to these 66 species.<br />
data(palm)<br />
palm is a list containing the 2 following objects:<br />
tre is a character string giving the phylogenetic tree in Newick format.<br />
traits is a data frame with 66 species (rows) and 7 traits (columns).<br />
Variables of palm$traits are the following ones:<br />
rord: specific richness with five ordered levels<br />
h: height in meter (squared transform)<br />
dqual: diameter at breast height in centimeter with five levels sout : subterranean, d1(0,<br />
5 cm), d2(5, 15 cm), d3(15, 30 cm) and d4(30, 100 cm)<br />
vfruit: fruit volume in mm 3 (logged transform)<br />
vgrain: seed volume in mm 3 (logged transform)<br />
aire: spatial distribution area (km 2 )<br />
alti: maximum altitude in meter (logged transform)<br />
<strong>Source</strong><br />
This data set was obtained by Clémentine Gimaret-Carpentier<br />
〈gimaret@biomserv.univ-lyon1.fr〉.<br />
Examples<br />
## Not run:<br />
data(palm)<br />
palm.phy
194 pap<br />
scalewt((palm$traits[,4])))<br />
names(w)[6]
pcaiv 195<br />
pcaiv<br />
Principal component analysis with respect to instrumental variables<br />
Description<br />
Usage<br />
performs a principal component analysis with respect to instrumental variables.<br />
pcaiv(dudi, df, scannf = TRUE, nf = 2)<br />
## S3 method for class 'pcaiv':<br />
plot(x, xax = 1, yax = 2, ...)<br />
## S3 method for class 'pcaiv':<br />
print(x, ...)<br />
Arguments<br />
dudi<br />
df<br />
scannf<br />
nf<br />
x<br />
Value<br />
xax<br />
yax<br />
a duality diagram, object of class dudi<br />
a data frame with the same rows<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
an object of class pcaiv<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
... further arguments passed to or from other methods<br />
returns an object of class pcaiv, sub-class of class dudi<br />
rank<br />
nf<br />
eig<br />
lw<br />
cw<br />
Y<br />
X<br />
tab<br />
c1<br />
as<br />
ls<br />
li<br />
an integer indicating the rank of the studied matrix<br />
an integer indicating the number of kept axes<br />
a vector with the all eigenvalues<br />
a numeric vector with the row weigths (from dudi)<br />
a numeric vector with the column weigths (from dudi)<br />
a data frame with the dependant variables<br />
a data frame with the explanatory variables<br />
a data frame with the modified array (projected variables)<br />
a data frame with the Pseudo Principal Axes (PPA)<br />
a data frame with the Principal axes of dudi$tab on PPA<br />
a data frame with the projections of lines of dudi$tab on PPA<br />
a data frame dudi$ls with the predicted values by X
196 pcaivortho<br />
fa<br />
l1<br />
co<br />
cor<br />
a data frame with the loadings (Constraint Principal Components as linear combinations<br />
of X<br />
data frame with the Constraint Principal Components (CPC)<br />
a data frame with the inner products between the CPC and Y<br />
a data frame with the correlations between the CPC and X<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Rao, C. R. (1964) <strong>The</strong> use and interpretation of principal component analysis in applied research.<br />
Sankhya, A 26, 329–359.<br />
Obadia, J. (1978) L’analyse en composantes explicatives. Revue de Statistique Appliquée, 24, 5–28.<br />
Lebreton, J. D., Sabatier, R., Banco G. and Bacou A. M. (1991) Principal component and correspondence<br />
analyses with respect to instrumental variables : an overview of their role in studies of<br />
structure-activity and species- environment relationships. In J. Devillers and W. Karcher, editors.<br />
Applied Multivariate Analysis in SAR and Environmental Studies, Kluwer Academic Publishers,<br />
85–114.<br />
Examples<br />
data(rhone)<br />
pca1
pcaivortho 197<br />
Arguments<br />
dudi<br />
df<br />
scannf<br />
nf<br />
a duality diagram, object of class dudi<br />
a data frame with the same rows<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
Value<br />
an object of class ’pcaivortho’ sub-class of class dudi<br />
rank<br />
nf<br />
eig<br />
lw<br />
cw<br />
Y<br />
X<br />
tab<br />
c1<br />
as<br />
ls<br />
li<br />
l1<br />
co<br />
param<br />
an integer indicating the rank of the studied matrix<br />
an integer indicating the number of kept axes<br />
a vector with the all eigenvalues<br />
a numeric vector with the row weigths (from dudi)<br />
a numeric vector with the column weigths (from dudi)<br />
a data frame with the dependant variables<br />
a data frame with the explanatory variables<br />
a data frame with the modified array (projected variables)<br />
a data frame with the Pseudo Principal Axes (PPA)<br />
a data frame with the Principal axis of dudi$tab on PAP<br />
a data frame with the projection of lines of dudi$tab on PPA<br />
a data frame dudi$ls with the predicted values by X<br />
a data frame with the Constraint Principal Components (CPC)<br />
a data frame with the inner product between the CPC and Y<br />
a data frame containing a summary<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Rao, C. R. (1964) <strong>The</strong> use and interpretation of principal component analysis in applied research.<br />
Sankhya, A 26, 329–359.<br />
Sabatier, R., Lebreton J. D. and Chessel D. (1989) Principal component analysis with instrumental<br />
variables as a tool for modelling composition data. In R. Coppi and S. Bolasco, editors. Multiway<br />
data analysis, Elsevier Science Publishers B.V., North-Holland, 341–352
198 pcoscaled<br />
Examples<br />
## Not run:<br />
par(mfrow = c(2,2))<br />
data(avimedi)<br />
cla
perthi02 199<br />
Author(s)<br />
Daniel Chessel<br />
References<br />
Gower, J. C. (1966) Some distance properties of latent root and vector methods used in multivariate<br />
analysis. Biometrika, 53, 325–338.<br />
Examples<br />
a
200 phylog<br />
Examples<br />
data(perthi02)<br />
plot(discrimin.coa(perthi02$tab, perthi02$cla, scan = FALSE))<br />
phylog<br />
Phylogeny<br />
Description<br />
Create and use objects of class phylog.<br />
phylog.extract returns objects of class phylog. It extracts sub-trees from a tree.<br />
phylog.permut returns objects of class phylog. It creates the different representations compatible<br />
with tree topology.<br />
Usage<br />
## S3 method for class 'phylog':<br />
print(x, ...)<br />
phylog.extract(phylog, node, distance = TRUE)<br />
phylog.permut(phylog, list.nodes = NULL, distance = TRUE)<br />
Arguments<br />
Value<br />
x, phylog : an object of class phylog<br />
... : further arguments passed to or from other methods<br />
node<br />
distance<br />
list.nodes<br />
Returns a list of class phylog :<br />
: a string of characters giving a node name. <strong>The</strong> functions extracts the tree<br />
rooted at this node.<br />
: if TRUE, both functions retain branch lengths. If FALSE, they returns tree<br />
with arbitrary branch lengths (each branch length equals one)<br />
: a list which elements are vectors of string of character corresponding to direct<br />
descendants of nodes. This list defines one representation compatible with tree<br />
topology among the set of possibilities.<br />
tre<br />
leaves<br />
nodes<br />
parts<br />
: a character string of the phylogenetic tree in Newick format whithout branch<br />
length values<br />
: a vector which names corresponds to leaves and values gives the distance<br />
between leaves and nodes closest to these leaves<br />
: a vector which names corresponds to nodes and values gives the distance between<br />
nodes and nodes closest to these leaves<br />
: a list which elements gives the direct descendants of each nodes
phylog 201<br />
paths<br />
droot<br />
call<br />
Wmat<br />
Wdist<br />
Wvalues<br />
Wscores<br />
Amat<br />
Avalues<br />
Adim<br />
Ascores<br />
Aparam<br />
Bindica<br />
Bscores<br />
Bvalues<br />
Blabels<br />
: a list which elements gives the path leading from the root to taxonomic units<br />
(leaves and nodes)<br />
: a vector which names corresponds to taxonomic units and values gives distance<br />
between taxonomic units and the root<br />
: call<br />
: a phylogenetic link matrix, generally called the covariance matrix. Matrix<br />
values W mat ij correspond to path length that lead from root to the first common<br />
ancestor of the two leaves i and j<br />
: a phylogenetic distance matrix of class ’dist’. Matrix values W dist ij correspond<br />
to √ d ij where d ij is the classical distance between two leaves i and<br />
j<br />
: a vector with the eigen values of Wmat<br />
: a data frame with eigen vectors of Wmat. This data frame defines an orthobasis<br />
that could be used to calculate the orthonormal decomposition of a biological<br />
trait on a tree.<br />
: a phylogenetic link matrix stemed from Abouheif’s test and defined in Ollier<br />
et al. (submited)<br />
: a vector with the eigen values of Amat<br />
: number of positive eigen values<br />
: a data frame with eigen vectors of Amat. This data frame defines an orthobasis<br />
that could be used to calculate the orthonormal decomposition of a biological<br />
trait on a tree.<br />
: a data frame with attributes associated to nodes.<br />
: a data frame giving for some taxonomic units the partition of leaves that is<br />
associated to its<br />
: a data frame giving an orthobasis defined by Ollier et al. (submited) that could<br />
be used to calculate the orthonormal decomposition of a biological trait on a<br />
tree.<br />
: a vector giving the degree of phylogenetic autocorrelation for each vectors of<br />
Bscores (Moran’s form calculated with the matrix Wmat)<br />
: a vector giving for each nodes the name of the vector of Bscores that is associated<br />
to its<br />
Author(s)<br />
Daniel Chessel<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
References<br />
Ollier, S., Couteron, P. and Chessel, D. (2005) Orthonormal transforms to detect and describe phylogenetic<br />
autocorrelation. Biometrics (in press).
202 plot.phylog<br />
See Also<br />
newick2phylog, plot.phylog<br />
Examples<br />
marthans.tre
plot.phylog 203<br />
f.phylog<br />
circle<br />
cleaves<br />
cnodes<br />
a size coefficient for tree size (a parameter to draw the tree in proportion to<br />
leaves label)<br />
a size coefficient for the outer circle<br />
a character size for plotting the points that represent the leaves, used with par("cex")*cleaves.<br />
If zero, no points are drawn<br />
a character size for plotting the points that represent the nodes, used with par("cex")*cnodes.<br />
If zero, no points are drawn<br />
labels.leaves<br />
a vector of strings of characters for the leaves labels<br />
clabel.leaves<br />
a character size for the leaves labels, used with par("cex")*clabel.leaves.<br />
If zero, no leaves labels are drawn<br />
labels.nodes a vector of strings of characters for the nodes labels<br />
clabel.nodes a character size for the nodes labels, used with par("cex")*clabel.nodes.<br />
If zero, no nodes labels are drawn<br />
sub<br />
csub<br />
possub<br />
draw.box<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
if TRUE draws a box around the current plot with the function box()<br />
... further arguments passed to or from other methods<br />
no.over<br />
a size coefficient for the number of representations<br />
Details<br />
<strong>The</strong> vector y is an argument of the function plot.phylog that ensures to plot one of the possible<br />
representations of a phylogeny. <strong>The</strong> vector y is a permutation of the set of leaves {1,2,. . . ,f}<br />
compatible with the phylogeny’s topology.<br />
Value<br />
<strong>The</strong> function enum.phylog returns a matrix with as many columns as leaves. Each row gives a<br />
permutation of the set of leaves {1,2,. . . ,f} compatible with the phylogeny’s topology.<br />
Author(s)<br />
Daniel Chessel<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
See Also<br />
phylog
204 plot.phylog<br />
Examples<br />
data(newick.eg)<br />
par(mfrow = c(3,2))<br />
for(i in 1:6) plot.phylog(newick2phylog(newick.eg[[i]], FALSE),<br />
clea = 2, clabel.l = 3, cnod = 2.5)<br />
par(mfrow = c(1,1))<br />
## Not run:<br />
par(mfrow = c(1,2))<br />
plot.phylog(newick2phylog(newick.eg[[11]], FALSE), clea = 1.5,<br />
clabel.l = 1.5, clabel.nod = 0.75, f = 0.8)<br />
plot.phylog(newick2phylog(newick.eg[[10]], FALSE), clabel.l = 0,<br />
clea = 0, cn = 0, f = 1)<br />
par(mfrow = c(1,1))<br />
## End(Not run)<br />
par(mfrow = c(2,2))<br />
w7
presid2002 205<br />
## Not run:<br />
# plot all the possible representations of a phylogenetic tree<br />
a
206 procella<br />
See Also<br />
This dataset is compatible with elec88 and cnc2003<br />
Examples<br />
data(presid2002)<br />
all((presid2002$tour2$Chirac + presid2002$tour2$Le_Pen) == presid2002$tour2$exprimes)<br />
## Not run:<br />
data(elec88)<br />
data(cnc2003)<br />
w1 = area.util.class(elec88$area, cnc2003$reg)<br />
par(mfrow = c(2,2))<br />
par(mar = c(0.1,0.1,0.1,0.1))<br />
area.plot(w1)<br />
w = scale(elec88$tab$Chirac)<br />
s.value(elec88$xy, w, add.plot = TRUE)<br />
scatterutil.sub("Chirac 1988 T1", csub = 2, "topleft")<br />
area.plot(w1)<br />
w = scale(presid2002$tour1$Chirac/ presid2002$tour1$exprimes)<br />
s.value(elec88$xy, w, add.plot = TRUE)<br />
scatterutil.sub("Chirac 2002 T1", csub = 2, "topleft")<br />
area.plot(w1)<br />
w = scale(elec88$tab$Mitterand)<br />
s.value(elec88$xy, w, add.plot = TRUE)<br />
scatterutil.sub("Mitterand 1988 T1", csub = 2, "topleft")<br />
area.plot(w1)<br />
w = scale(presid2002$tour2$Chirac/ presid2002$tour2$exprimes)<br />
s.value(elec88$xy, w, add.plot = TRUE)<br />
scatterutil.sub("Chirac 2002 T2", csub = 2, "topleft")<br />
## End(Not run)<br />
procella<br />
Phylogeny and quantitative traits of birds<br />
Description<br />
This data set describes the phylogeny of 19 birds as reported by Bried et al. (2002). It also gives 6<br />
traits corresponding to these 19 species.<br />
Usage<br />
data(procella)
procuste 207<br />
Format<br />
procella is a list containing the 2 following objects:<br />
tre is a character string giving the phylogenetic tree in Newick format.<br />
traits is a data frame with 19 species and 6 traits<br />
Details<br />
Variables of procella$traits are the following ones:<br />
site.fid: a numeric vector that describes the percentage of site fidelity<br />
mate.fid: a numeric vector that describes the percentage of mate fidelity<br />
mass: an integer vector that describes the adult body weight (g)<br />
ALE: a numeric vector that describes the adult life expectancy (years)<br />
BF: a numeric vector that describes the breeding frequencies<br />
col.size: an integer vector that describes the colony size (no nests monitored)<br />
References<br />
Bried, J., Pontier, D. and Jouventin, P. (2002) Mate fidelity in monogamus birds: a re-examination<br />
of the Procellariiformes. Animal Behaviour, 65, 235–246.<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps037.pdf (in French).<br />
Examples<br />
data(procella)<br />
pro.phy
208 procuste<br />
Usage<br />
procuste(df1, df2, scale = TRUE, nf = 4, tol = 1e-07)<br />
## S3 method for class 'procuste':<br />
plot(x, xax = 1, yax = 2, ...)<br />
## S3 method for class 'procuste':<br />
print(x, ...)<br />
Arguments<br />
df1, df2<br />
two data frames with the same rows<br />
scale a logical value indicating whether a transformation by the Gower’s scaling (1971)<br />
should be applied<br />
nf<br />
tol<br />
x<br />
Value<br />
xax<br />
yax<br />
an integer indicating the number of kept axes<br />
a tolerance threshold to test whether the distance matrix is Euclidean : an eigenvalue<br />
is considered positive if it is larger than -tol*lambda1 where lambda1<br />
is the largest eigenvalue.<br />
an objet of class procuste<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
... further arguments passed to or from other methods<br />
returns a list of the class procuste with 9 components<br />
d<br />
rank<br />
nfact<br />
tab1<br />
tab2<br />
a numeric vector of the singular values<br />
an integer indicating the rank of the crossed matrix<br />
an integer indicating the number of kept axes<br />
a data frame with the array 1, possibly scaled<br />
a data frame with the array 2, possibly scaled<br />
rot1 a data frame with the result of the rotation from array 1 to array 2<br />
rot2 a data frame with the result of the rotation from array 2 to array 1<br />
load1 a data frame with the loadings of array 1<br />
load2 a data frame with the loadings of array 2<br />
scor1 a data frame with the scores of array 1<br />
scor2 a data frame with the scores of array 2<br />
call<br />
Author(s)<br />
a call order of the analysis<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉
procuste.randtest 209<br />
References<br />
Digby, P. G. N. and Kempton, R. A. (1987) Multivariate Analysis of Ecological Communities. Population<br />
and Community Biology Series, Chapman and Hall, London.<br />
Gower, J.C. (1971) Statistical methods of comparing different multivariate analyses of the same<br />
data. In Mathematics in the archaeological and historical sciences, Hodson, F.R, Kendall, D.G. &<br />
Tautu, P. (Eds.) University Press, Edinburgh, 138–149.<br />
Schönemann, P.H. (1968) On two-sided Procustes problems. Psychometrika, 33, 19–34.<br />
Torre, F. and Chessel, D. (1994) Co-structure de deux tableaux totalement appariés. Revue de<br />
Statistique Appliquée, 43, 109–121.<br />
Dray, S., Chessel, D. and Thioulouse, J. (2003) Procustean co-inertia analysis for the linking of<br />
multivariate datasets. Ecoscience, 10, 1, 110-119.<br />
Examples<br />
data(macaca)<br />
par(mfrow = c(2,2))<br />
pro1
210 procuste.rtest<br />
Description<br />
performs a Monte-Carlo Test on the sum of the singular values of a procustean rotation.<br />
Usage<br />
procuste.randtest(df1, df2, nrepet = 999)<br />
Arguments<br />
df1<br />
df2<br />
nrepet<br />
a data frame<br />
a data frame<br />
the number of permutations<br />
Value<br />
returns a list of class randtest<br />
Author(s)<br />
Jean Thioulouse 〈<strong>ade4</strong>-jt@biomserv.univ-lyon1.fr〉<br />
References<br />
Jackson, D.A. (1995) PROTEST: a PROcustean randomization TEST of community environment<br />
concordance. Ecosciences, 2, 297–303.<br />
Examples<br />
data(doubs)<br />
pca1
pta 211<br />
Arguments<br />
df1<br />
df2<br />
nrepet<br />
a data frame<br />
a data frame<br />
the number of permutations<br />
Value<br />
returns a list of class rtest<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Jackson, D.A. (1995) PROTEST: a PROcustean randomization TEST of community environment<br />
concordance. Ecosciences, 2, 297–303.<br />
Examples<br />
data(doubs)<br />
pca1
212 pta<br />
Arguments<br />
X<br />
scannf<br />
nf<br />
x<br />
xax, yax<br />
option<br />
an object of class ktab where the arrays have 1) the same dimensions 2) the<br />
same names for columns 3) the same column weightings<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
an object of class ’pta’<br />
the numbers of the x-axis and the y-axis<br />
an integer between 1 and 4, otherwise the 4 components of the plot are displayed<br />
... further arguments passed to or from other methods<br />
Value<br />
returns a list of class ’pta’, sub-class of ’dudi’ containing :<br />
RV<br />
RV.eig<br />
RV.coo<br />
tab.names<br />
nf<br />
rank<br />
tabw<br />
cw<br />
lw<br />
eig<br />
cos2<br />
tab<br />
li<br />
l1<br />
co<br />
c1<br />
Tli<br />
Tco<br />
Tcomp<br />
Tax<br />
TL<br />
TC<br />
T4<br />
a matrix with the all RV coefficients<br />
a numeric vector with the all eigenvalues (interstructure)<br />
a data frame with the scores of the arrays<br />
a vector of characters with the array names<br />
an integer indicating the number of kept axes<br />
an integer indicating the rank of the studied matrix<br />
a numeric vector with the array weights<br />
a numeric vector with the column weights<br />
a numeric vector with the row weights<br />
a numeric vector with the all eigenvalues (compromis)<br />
a numeric vector with the cos 2 between compromise and arrays<br />
a data frame with the modified array<br />
a data frame with the row coordinates<br />
a data frame with the row normed scores<br />
a data frame with the column coordinates<br />
a data frame with the column normed scores<br />
a data frame with the row coordinates (each table)<br />
a data frame with the column coordinates (each table)<br />
a data frame with the principal components (each table)<br />
a data frame with the principal axes (each table)<br />
a data frame with the factors for Tli<br />
a data frame with the factors for Tco<br />
a data frame with the factors for Tax and Tcomp
quasieuclid 213<br />
Author(s)<br />
Pierre Bady 〈pierre.bady@univ-lyon1.fr〉<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Blanc, L., Chessel, D. and Dolédec, S. (1998) Etude de la stabilité temporelle des structures spatiales<br />
par Analyse d’une série de tableaux faunistiques totalement appariés. Bulletin Français de la<br />
Pêche et de la Pisciculture, 348, 1–21.<br />
Thioulouse, J., and D. Chessel. 1987. Les analyses multi-tableaux en écologie factorielle. I De<br />
la typologie d’état à la typologie de fonctionnement par l’analyse triadique. Acta Oecologica, Oecologia<br />
Generalis, 8, 463–480.<br />
Examples<br />
data(meaudret)<br />
wit1
214 randEH<br />
Value<br />
object of class dist containing a Euclidean distance matrice<br />
Author(s)<br />
Daniel Chessel<br />
Stéphane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
Examples<br />
data(yanomama)<br />
geo
andtest-internal 215<br />
References<br />
Nee, S. and May, R.M. (1997) Extinction and the loss of evolutionary history. Science 278, 692–<br />
694.<br />
Pavoine, S., Ollier, S. and Dufour, A.-B. (2005) Is the originality of a species measurable? Ecology<br />
Letters, 8, 579–586.<br />
See Also<br />
optimEH<br />
Examples<br />
data(carni70)<br />
carni70.phy
216 randtest<br />
randtest<br />
Class of the Permutation Tests (in C).<br />
Description<br />
randtest is a generic function. It proposes methods for the following objects between, discrimin,<br />
coinertia ...<br />
Usage<br />
randtest(xtest, ...)<br />
## S3 method for class 'randtest':<br />
plot(x, nclass = 10, coeff = 1, ...)<br />
as.randtest (sim, obs,alter=c("greater", "less", "two-sided"), call = match.cal<br />
## S3 method for class 'randtest':<br />
print(x, ...)<br />
Arguments<br />
xtest<br />
x<br />
an object used to select a method<br />
an object of class randtest<br />
... ... further arguments passed to or from other methods; in plot.randtest<br />
to hist<br />
nclass<br />
coeff<br />
sim<br />
obs<br />
alter<br />
call<br />
a number of intervals for the histogram<br />
to fit the magnitude of the graph<br />
a numeric vector of simulated values<br />
a numeric vector of an observed value<br />
a character string specifying the alternative hypothesis, must be one of "greater"<br />
(default), "less" or "two-sided"<br />
a call order<br />
Value<br />
as.randtest returns a list of class randtest<br />
plot.randtest draws the simulated values histograms and the position of the observed value<br />
See Also<br />
mantel.randtest, procuste.randtest, rtest
andtest.amova 217<br />
Examples<br />
par(mfrow = c(2,2))<br />
for (x0 in c(2.4,3.4,5.4,20.4)) {<br />
l0
218 randtest.between<br />
randtest.between<br />
Monte-Carlo Test on the between-groups inertia percentage (in C).<br />
Description<br />
Performs a Monte-Carlo test on the between-groups inertia percentage.<br />
Usage<br />
## S3 method for class 'between':<br />
randtest(xtest, nrepet = 999, ...)<br />
Arguments<br />
xtest an object of class between<br />
nrepet the number of permutations<br />
... further arguments passed to or from other methods<br />
Value<br />
a list of the class randtest<br />
Author(s)<br />
Jean Thioulouse 〈<strong>ade4</strong>-jt@biomserv.univ-lyon1.fr〉<br />
References<br />
Romesburg, H. C. (1985) Exploring, confirming and randomization tests. Computers and Geosciences,<br />
11, 19–37.<br />
Examples<br />
data(meaudret)<br />
pca1
andtest.coinertia 219<br />
randtest.coinertia Monte-Carlo test on a Co-inertia analysis (in C).<br />
Description<br />
Performs a Monte-Carlo test on a Co-inertia analysis.<br />
Usage<br />
## S3 method for class 'coinertia':<br />
randtest(xtest, nrepet = 999, fixed=0, ...)<br />
Arguments<br />
Value<br />
xtest<br />
nrepet<br />
fixed<br />
an object of class coinertia<br />
the number of permutations<br />
when non uniform row weights are used in the coinertia analysis, this parameter<br />
must be the number of the table that should be kept fixed in the permutations<br />
... further arguments passed to or from other methods<br />
a list of the class randtest<br />
Note<br />
A testing procedure based on the total coinertia of the analysis is available by the function randtest.coinertia.<br />
<strong>The</strong> function allows to deal with various analyses for the two tables. <strong>The</strong> test is based on random<br />
permutations of the rows of the two tables. If the row weights are not uniform, mean and variances<br />
are recomputed for each permutation (PCA); for MCA, tables are recentred and column weights are<br />
recomputed. If weights are computed using the data contained in one table (e.g. COA), you must<br />
fix this table and permute only the rows of the other table. <strong>The</strong> case of decentred PCA (PCA where<br />
centers are entered by the user) is not yet implemented. If you want to use the testing procedure for<br />
this case, you must firstly center the table and then perform a non-centered PCA on the modified<br />
table. <strong>The</strong> case where one table is treated by hill-smith analysis (mix of quantitative and qualitative<br />
variables) will be soon implemented.<br />
Author(s)<br />
Jean Thioulouse 〈<strong>ade4</strong>-jt@biomserv.univ-lyon1.fr〉 modified by Stephane Dray 〈dray@biomserv.univlyon1.fr〉<br />
References<br />
Dolédec, S. and Chessel, D. (1994) Co-inertia analysis: an alternative method for studying speciesenvironment<br />
relationships. Freshwater Biology, 31, 277–294.
220 randtest.discrimin<br />
Examples<br />
data(doubs)<br />
dudi1
ankrock 221<br />
# Df Pillai approx F num Df den Df Pr(>F)<br />
# meaudret$plan$dat 3 2.73 11.30 27 30 1.6e-09 ***<br />
# Residuals 16<br />
# ---<br />
# Signif. codes: 0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1<br />
# 2.731/9 = 0.3034<br />
rankrock<br />
Ordination Table<br />
Description<br />
This data set gives the classification in order of preference of 10 music groups by 51 students.<br />
Usage<br />
data(rankrock)<br />
Format<br />
A data frame with 10 rows and 51 columns.<br />
Each column contains the rank (1 for the favorite, . . . , 10 for the less appreciated)<br />
attributed to the group by a student.<br />
Examples<br />
data(rankrock)<br />
dudi1
222 reconst<br />
Arguments<br />
dudi<br />
an object of class dudi used to select a method: pca or coa<br />
nf<br />
an integer indicating the number of kept axes for the reconstitution<br />
... further arguments passed to or from other methods<br />
Value<br />
returns a data frame containing the reconstituted data<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Gabriel, K.R. (1978) Least-squares approximation of matrices by additive and multiplicative models.<br />
Journal of the Royal Statistical Society, B , 40, 186–196.<br />
Examples<br />
data(rhone)<br />
dd1
hone 223<br />
rhone<br />
Physico-Chemistry Data<br />
Description<br />
This data set gives for 39 water samples a physico-chemical description with the number of sample<br />
date and the flows of three tributaries.<br />
Usage<br />
data(rhone)<br />
Format<br />
rhone is a list of 3 components.<br />
tab is a data frame with 39 water samples and 15 physico-chemical variables.<br />
date is a vector of the sample date (in days).<br />
disch is a data frame with 39 water samples and the flows of the three tributaries.<br />
<strong>Source</strong><br />
Carrel, G., Barthelemy, D., Auda, Y. and Chessel, D. (1986) Approche graphique de l’analyse<br />
en composantes principales normée : utilisation en hydrobiologie. Acta Oecologica, Oecologia<br />
Generalis, 7, 189–203.<br />
Examples<br />
data(rhone)<br />
pca1
224 rlq<br />
rlq<br />
RLQ analysis<br />
Description<br />
Usage<br />
RLQ analysis performs a double inertia analysis of two arrays (R and Q) with a link expressed by a<br />
contingency table (L). <strong>The</strong> rows of L correspond to the rows of R and the columns of Q correspond<br />
to the rows of Q.<br />
rlq(dudiR, dudiL, dudiQ, scannf = TRUE, nf = 2)<br />
## S3 method for class 'rlq':<br />
print(x, ...)<br />
## S3 method for class 'rlq':<br />
plot(x, xax = 1, yax = 2, ...)<br />
## S3 method for class 'rlq':<br />
summary(object, ...)<br />
## S3 method for class 'rlq':<br />
randtest(xtest,nrepet = 999, ...)<br />
Arguments<br />
dudiR<br />
dudiL<br />
dudiQ<br />
scannf<br />
nf<br />
x<br />
Value<br />
xax<br />
yax<br />
object<br />
xtest<br />
nrepet<br />
a duality diagram providing from one of the functions dudi.hillsmith, dudi.pca,<br />
. . .<br />
a duality diagram of the function dudi.coa<br />
a duality diagram providing from one of the functions dudi.hillsmith, dudi.pca,<br />
. . .<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
an rlq object<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
an rlq object<br />
an rlq object<br />
the number of permutations<br />
... further arguments passed to or from other methods<br />
Returns a list of class ’dudi’, sub-class ’rlq’ containing:<br />
call<br />
rank<br />
call<br />
rank
lq 225<br />
nf<br />
RV<br />
eig<br />
lw<br />
cw<br />
tab<br />
li<br />
l1<br />
co<br />
c1<br />
lR<br />
mR<br />
lQ<br />
mQ<br />
aR<br />
aQ<br />
a numeric value indicating the number of kept axes<br />
a numeric value, the RV coefficient<br />
a numeric vector with all the eigenvalues<br />
a numeric vector with the rows weigths (crossed array)<br />
a numeric vector with the columns weigths (crossed array)<br />
a crossed array (CA)<br />
R col = CA row: coordinates<br />
R col = CA row: normed scores<br />
Q col = CA column: coordinates<br />
Q col = CA column: normed scores<br />
the row coordinates (R)<br />
the normed row scores (R)<br />
the row coordinates (Q)<br />
the normed row scores (Q)<br />
the axis onto co-inertia axis (R)<br />
the axis onto co-inertia axis (Q)<br />
WARNING<br />
Note<br />
IMPORTANT : row weights for dudiR and dudiQ must be taken from dudiL.<br />
A testing procedure based on the total coinertia of the RLQ analysis is available by the function<br />
randtest.rlq. <strong>The</strong> function allows to deal with various analyses for tables R and Q. Means and<br />
variances are recomputed for each permutation (PCA); for MCA, tables are recentred and column<br />
weights are recomputed.<strong>The</strong> case of decentred PCA (PCA where centers are entered by the user)<br />
for R or Q is not yet implemented. If you want to use the testing procedure for this case, you must<br />
firstly center the table and then perform a non-centered PCA on the modified table.<br />
Author(s)<br />
Stephane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Doledec, S., Chessel, D., ter Braak, C.J.F. and Champely, S. (1996) Matching species traits to environmental<br />
variables: a new three-table ordination method. Environmental and Ecological Statistics,<br />
3, 143–166.<br />
Dray, S., Pettorelli, N., Chessel, D. (2002) Matching data sets from two different spatial samplings.<br />
Journal of Vegetation Science, 13, 867–874.<br />
See Also<br />
coinertia
226 rpjdl<br />
Examples<br />
data(aviurba)<br />
coa1
test 227<br />
Examples<br />
## Not run:<br />
data(rpjdl)<br />
xy
228 rtest.between<br />
Value<br />
as.rtest returns a list of class rtest<br />
plot.rtest draws the simulated values histograms and the position of the observed value<br />
Author(s)<br />
See Also<br />
Daniel Chessel<br />
RV.rtest, mantel.rtest, procuste.rtest, randtest<br />
Examples<br />
par(mfrow = c(2,2))<br />
for (x0 in c(2.4,3.4,5.4,20.4)) {<br />
l0
test.discrimin 229<br />
References<br />
Romesburg, H. C. (1985) Exploring, confirming and randomization tests. Computers and Geosciences,<br />
11, 19–37.<br />
Examples<br />
data(meaudret)<br />
pca1
230 s.arrow<br />
#Based on 999 replicates<br />
#Simulated p-value: 0.001<br />
plot(rand1, main = "Monte-Carlo test")<br />
summary.manova(manova(as.matrix(meaudret$mil)~meaudret$plan$dat), "Pillai")<br />
# Df Pillai approx F num Df den Df Pr(>F)<br />
# meaudret$plan$dat 3 2.73 11.30 27 30 1.6e-09 ***<br />
# Residuals 16<br />
# ---<br />
# Signif. codes: 0 `***' 0.001 `**' 0.01 `*' 0.05 `.' 0.1 ` ' 1<br />
# 2.731/9 = 0.3034<br />
s.arrow<br />
Plot of the factorial maps for the projection of a vector basis<br />
Description<br />
Usage<br />
performs the scatter diagrams of the projection of a vector basis.<br />
s.arrow(dfxy, xax = 1, yax = 2, label = row.names(dfxy),<br />
clabel = 1, pch = 20, cpoint = 0, boxes = TRUE, edge = TRUE, origin = c(0,0),<br />
xlim = NULL, ylim = NULL, grid = TRUE, addaxes = TRUE, cgrid = 1,<br />
sub = "", csub = 1.25, possub = "bottomleft", pixmap = NULL,<br />
contour = NULL, area = NULL, add.plot = FALSE)<br />
Arguments<br />
dfxy<br />
xax<br />
yax<br />
label<br />
clabel<br />
pch<br />
cpoint<br />
boxes<br />
edge<br />
origin<br />
xlim<br />
ylim<br />
grid<br />
a data frame containing the two columns for the axes<br />
the column number of x in dfxy<br />
the column number of y in dfxy<br />
a vector of strings of characters for the point labels<br />
if not NULL, a character size for the labels used with par("cex")*clabel<br />
if cpoint > 0, an integer specifying the symbol or the single character to be<br />
used in plotting points<br />
a character size for plotting the points, used with par("cex")*cpoint. If zero,<br />
no points are drawn.<br />
if TRUE, labels are framed<br />
a logical value indicating whether the arrows should be plotted<br />
the fixed point in the graph space, by default c(0,0) the origin of axes. <strong>The</strong><br />
arrows begin at cent.<br />
the ranges to be encompassed by the x-axis, if NULL they are computed<br />
the ranges to be encompassed by the y-axis, if NULL they are computed<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn
s.chull 231<br />
addaxes<br />
cgrid<br />
sub<br />
csub<br />
possub<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
a logical value indicating whether the axes should be plotted<br />
a character size, parameter used with par("cex")*cgrid, to indicate the<br />
mesh of the grid<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the legend position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
an object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
Value<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
s.arrow(cbind.data.frame(runif(55,-2,3), runif(55,-3,2)))<br />
s.chull<br />
Plot of the factorial maps with polygons of contour by level of a factor<br />
Description<br />
performs the scatter diagrams with polygons of contour by level of a factor.<br />
Usage<br />
s.chull(dfxy, fac, xax = 1, yax = 2,<br />
optchull = c(0.25, 0.5, 0.75, 1), label = levels(fac), clabel = 1,<br />
cpoint = 0, col = rep(1, length(levels(fac))), xlim = NULL, ylim = NULL,<br />
grid = TRUE, addaxes = TRUE, origin = c(0,0), include.origin = TRUE,<br />
sub = "", csub = 1, possub = "bottomleft", cgrid = 1, pixmap = NULL,<br />
contour = NULL, area = NULL, add.plot = FALSE)
232 s.chull<br />
Arguments<br />
dfxy<br />
fac<br />
xax<br />
yax<br />
optchull<br />
label<br />
clabel<br />
cpoint<br />
col<br />
xlim<br />
ylim<br />
grid<br />
addaxes<br />
origin<br />
a data frame containing the two columns for the axes<br />
a factor partioning the rows of the data frame in classes<br />
the column number of x in dfxy<br />
the column number of y in dfxy<br />
the number of convex hulls and their interval<br />
a vector of strings of characters for the point labels<br />
if not NULL, a character size for the labels, used with par("cex")*clabel<br />
a character size for plotting the points, used with par("cex")*cpoint. If<br />
zero, no points are drawn<br />
a vector of colors used to draw each class in a different color<br />
the ranges to be encompassed by the x axis, if NULL, they are computed<br />
the ranges to be encompassed by the y axis, if NULL they are computed<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a logical value indicating whether the axes should be plotted<br />
the fixed point in the graph space, for example c(0,0) the origin axes<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
sub<br />
csub<br />
possub<br />
cgrid<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
a character size, parameter used with par("cex")* cgrid to indicate the mesh<br />
of the grid<br />
an object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
Value<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel
s.class 233<br />
Examples<br />
xy 0)<br />
coul 0, an integer specifying the symbol or the single character to be<br />
used in plotting points<br />
a vector of colors used to draw each class in a different color<br />
the ranges to be encompassed by the x, if NULL they are computed<br />
the ranges to be encompassed by the y, if NULL they are computed
234 s.class<br />
Value<br />
grid<br />
addaxes<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a logical value indicating whether the axes should be plotted<br />
origin the fixed point in the graph space, for example c(0,0) the origin axes<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
sub<br />
csub<br />
possub<br />
cgrid<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
a character size, parameter used with par("cex")* cgrid to indicate the mesh<br />
of the grid<br />
an object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
xy 0)<br />
coul
s.corcircle 235<br />
possub = "bottomright", cell = 0, cstar = 0.5, cgrid = 0, csub = 1.5)<br />
s.class(dudi1$li, banque[,20], csta = 0, cell = 2, cgrid = 0,<br />
clab = 1.5)<br />
s.class(dudi1$li, banque[,20], sub = names(banque)[20],<br />
possub = "topright", cgrid = 0, col = coul)<br />
par(mfrow = c(1,1))<br />
par(mfrow = n2mfrow(ncol(banque)))<br />
for (i in 1:(ncol(banque)))<br />
s.class(dudi1$li, banque[,i], clab = 1.5, sub = names(banque)[i],<br />
csub = 2, possub = "topleft", cgrid = 0, csta = 0, cpoi = 0)<br />
s.label(dudi1$li, clab = 0, sub = "Common background")<br />
par(mfrow = c(1,1))<br />
## End(Not run)<br />
s.corcircle<br />
Plot of the factorial maps of a correlation circle<br />
Description<br />
performs the scatter diagram of a correlation circle.<br />
Usage<br />
s.corcircle(dfxy, xax = 1, yax = 2, label = row.names(df),<br />
clabel = 1, grid = TRUE, sub = "", csub = 1, possub = "bottomleft",<br />
cgrid = 0, fullcircle = TRUE, box = FALSE, add.plot = FALSE)<br />
Arguments<br />
dfxy<br />
xax<br />
yax<br />
label<br />
clabel<br />
grid<br />
sub<br />
csub<br />
possub<br />
cgrid<br />
fullcircle<br />
box<br />
add.plot<br />
a data frame with two coordinates<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
a vector of strings of characters for the point labels<br />
if not NULL, a character size for the labels, used with par("cex")*clabel<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
a character size, parameter used with par("cex")*cgrid to indicate the mesh of<br />
the grid<br />
a logical value indicating whether the complete circle sould be drawn<br />
a logical value indcating whether a box should be drawn<br />
if TRUE uses the current graphics window
236 s.distri<br />
Value<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data (olympic)<br />
dudi1
s.distri 237<br />
Value<br />
clabel<br />
cpoint<br />
pch<br />
xlim<br />
ylim<br />
grid<br />
addaxes<br />
if not NULL, a character size for the labels, used with par("cex")*clabel<br />
a character size for plotting the points, used with par("cex")*cpoint. If<br />
zero, no points are drawn<br />
if cpoint > 0, an integer specifying the symbol or the single character to be<br />
used in plotting points<br />
the ranges to be encompassed by the x, if NULL they are computed<br />
the ranges to be encompassed by the y, if NULL they are computed<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a logical value indicating whether the axes should be plotted<br />
origin the fixed point in the graph space, for example c(0,0) the origin axes<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
sub<br />
csub<br />
possub<br />
cgrid<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
a character size, parameter used with par("cex")* cgrid to indicate the mesh<br />
of the grid<br />
an object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
xy 0))<br />
w2 0) & (xy$y < 0)) * (1 - xy$y) * xy$x<br />
w3 0)) * (1 - xy$x) * xy$y<br />
w4
238 s.hist<br />
distri
s.image 239<br />
Examples<br />
data(rpjdl)<br />
coa1
240 s.image<br />
Value<br />
sub<br />
csub<br />
possub<br />
neig<br />
cneig<br />
image.plot<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
an object of class neig<br />
a size for the neighbouring graph lines used with par("lwd")*cneig<br />
if TRUE, the image is traced<br />
contour.plot if TRUE, the contour lines are plotted<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
an object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
if (require(splancs, quiet = TRUE)){<br />
wxy=data.frame(expand.grid(-3:3,-3:3))<br />
names(wxy)=c("x","y")<br />
z=(1/sqrt(2))*exp(-(wxy$x^2+wxy$y^2)/2)<br />
par(mfrow=c(2,2))<br />
s.value(wxy,z)<br />
s.image(wxy,z)<br />
s.image(wxy,z,kgrid=5)<br />
s.image(wxy,z,kgrid=15)<br />
}<br />
## Not run:<br />
data(t3012)<br />
if (require(splancs, quiet = TRUE)){<br />
par(mfrow = c(4,4))<br />
for(k in 1:12) s.image(t3012$xy,scalewt(t3012$temp[,k]), kgrid = 3)<br />
par(mfrow = c(1,1))<br />
}<br />
data(elec88)<br />
if (require(splancs, quiet = TRUE)){<br />
par(mfrow = c(4,4))<br />
for(k in 1:12)
s.kde2d 241<br />
s.image(t3012$xy, scalewt(t3012$temp[,k]), kgrid = 3, sub = names(t3012$temp)[k],<br />
csub = 3, area = elec88$area)<br />
par(mfrow = c(1,1))<br />
}<br />
## End(Not run)<br />
s.kde2d<br />
Scatter Plot with Kernel Density Estimate<br />
Description<br />
Usage<br />
performs a scatter of points without labels by a kernel Density Estimation in One or Two Dimensions<br />
s.kde2d(dfxy, xax = 1, yax = 2, pch = 20, cpoint = 1, neig = NULL, cneig = 2,<br />
xlim = NULL, ylim = NULL, grid = TRUE, addaxes = TRUE, cgrid = 1,<br />
include.origin = TRUE, origin = c(0, 0), sub = "", csub = 1.25,<br />
possub = "bottomleft", pixmap = NULL, contour = NULL,<br />
area = NULL, add.plot = FALSE)<br />
Arguments<br />
dfxy<br />
xax<br />
yax<br />
pch<br />
cpoint<br />
neig<br />
cneig<br />
xlim<br />
ylim<br />
grid<br />
addaxes<br />
a data frame with at least two coordinates<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
if cpoint > 0, an integer specifying the symbol or the single character to be<br />
used in plotting points<br />
a character size for plotting the points, used with par("cex")*cpoint. If<br />
zero, no points are drawn<br />
a neighbouring graph<br />
a size for the neighbouring graph lines used with par("lwd")*cneig<br />
the ranges to be encompassed by the x axis, if NULL, they are computed<br />
the ranges to be encompassed by the y axis, if NULL, they are computed<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a logical value indicating whether the axes should be plotted<br />
cgrid a character size, parameter used with par("cex")* ’cgrid’ to indicate the mesh of<br />
the grid<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
origin<br />
the fixed point in the graph space, for example c(0,0) the origin axes
242 s.label<br />
sub<br />
csub<br />
possub<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
an object pixmap displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
Value<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
# To recognize groups of points<br />
data(casitas)<br />
casitas.fuz = fuzzygenet(casitas)<br />
casitas.pop
s.label 243<br />
Arguments<br />
Value<br />
dfxy<br />
xax<br />
yax<br />
label<br />
clabel<br />
pch<br />
cpoint<br />
boxes<br />
neig<br />
cneig<br />
xlim<br />
ylim<br />
grid<br />
addaxes<br />
a data frame with at least two coordinates<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
a vector of strings of characters for the point labels<br />
if not NULL, a character size for the labels, used with par("cex")*clabel<br />
if cpoint > 0, an integer specifying the symbol or the single character to be<br />
used in plotting points<br />
a character size for plotting the points, used with par("cex")*cpoint. If<br />
zero, no points are drawn<br />
if TRUE, labels are framed<br />
a neighbouring graph<br />
a size for the neighbouring graph lines used with par("lwd")*cneig<br />
the ranges to be encompassed by the x axis, if NULL, they are computed<br />
the ranges to be encompassed by the y axis, if NULL, they are computed<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a logical value indicating whether the axes should be plotted<br />
cgrid a character size, parameter used with par("cex")* cgrid to indicate the mesh<br />
of the grid<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
origin<br />
sub<br />
csub<br />
possub<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
the fixed point in the graph space, for example c(0,0) the origin axes<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
an object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window
244 s.logo<br />
Examples<br />
layout(matrix(c(1,2,3,2), 2, 2))<br />
data(atlas)<br />
s.label(atlas$xy, lab = atlas$names.district,<br />
area = atlas$area, inc = FALSE, addax = FALSE)<br />
data(mafragh)<br />
s.label(mafragh$xy, inc = FALSE, neig = mafragh$neig, addax = FALSE)<br />
data(irishdata)<br />
s.label(irishdata$xy, inc = FALSE, contour = irishdata$contour,<br />
addax = FALSE)<br />
par(mfrow = c(2,2))<br />
cha
s.logo 245<br />
Value<br />
xax<br />
yax<br />
neig<br />
cneig<br />
xlim<br />
ylim<br />
grid<br />
addaxes<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
a neighbouring graph<br />
a size for the neighbouring graph lines used with par("lwd")*cneig<br />
the ranges to be encompassed by the x axis, if NULL, they are computed<br />
the ranges to be encompassed by the y axis, if NULL, they are computed<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a logical value indicating whether the axes should be plotted<br />
cgrid a character size, parameter used with par("cex")* cgrid to indicate the mesh<br />
of the grid<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
origin<br />
sub<br />
csub<br />
possub<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
the fixed point in the graph space, for example c(0,0) the origin axes<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
an object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
Daniel Chessel and Thibaut Jombart 〈jombart@biomserv.univ-lyon1.fr〉<br />
Examples<br />
if(require(pixmap, quiet=TRUE)){<br />
data(ggtortoises)<br />
a1
246 s.match<br />
}<br />
data(capitales)<br />
index
s.multinom 247<br />
Value<br />
cgrid a character size, parameter used with par("cex")* cgrid to indicate the mesh<br />
of the grid<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
origin<br />
sub<br />
csub<br />
possub<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
<strong>The</strong> matched call.<br />
the fixed point in the graph space, for example c(0,0) the origin axes<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
aan object pixmap displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
X
248 s.multinom<br />
Usage<br />
s.multinom(dfxy, dfrowprof, translate = FALSE, xax = 1, yax = 2,<br />
labelcat = row.names(dfxy), clabelcat = 1, cpointcat = if (clabelcat == 0) 2 els<br />
labelrowprof = row.names(dfrowprof), clabelrowprof = 0.75,<br />
cpointrowprof = if (clabelrowprof == 0) 2 else 0, pchrowprof = 20,<br />
coulrowprof = grey(0.8), proba = 0.95, n.sample = apply(dfrowprof, 1, sum),<br />
axesell = TRUE, ...)<br />
Arguments<br />
dfxy<br />
dfrowprof<br />
translate<br />
xax<br />
yax<br />
labelcat<br />
clabelcat<br />
cpointcat<br />
dfxy is a data frame containing at least two numerical variables. <strong>The</strong> rows of<br />
dfxy are categories such as 1,2 and 3 in the triangular plot.<br />
dfrowprof is a data frame whose the columns are the rows of dfxy. <strong>The</strong><br />
rows of dfxy are profiles or frequency distributions on the categories. <strong>The</strong><br />
column number of dfrowprof must be equal to the row number of dfxy.<br />
row.names(dfxy) and names(dfrowprof) must be identical.<br />
a logical value indicating whether the plot should be translated(TRUE) or not.<br />
<strong>The</strong> origin becomes the gravity center weighted by profiles.<br />
the column number of dfxy for the x-axis<br />
the column number of dfxy for the y-axis<br />
a vector of strings of characters for the labels of categories<br />
an integer specifying the character size for the labels of categories, used with<br />
par("cex")*clabelcat<br />
an integer specifying the character size for the points showing the categories,<br />
used with par("cex")*cpointcat<br />
labelrowprof a vector of strings of characters for the labels of profiles (rows of dfrowprof)<br />
clabelrowprof<br />
an integer specifying the character size for the labels of profiles used with par("cex")*clabelrowprof<br />
cpointrowprof<br />
an integer specifying the character size for the points representative of the profiles<br />
used with par("cex")*cpointrowprof<br />
pchrowprof<br />
coulrowprof<br />
proba<br />
either an integer specifying a symbol or a single character to be used for the<br />
profile labels<br />
a vector of colors used for ellipses, possibly recycled<br />
a value lying between 0.500 and 0.999 to draw a confidence interval<br />
n.sample a vector containing the sample size, possibly recycled. Used n.sample = 0<br />
if the profiles are not issued from a multinomial distribution and that confidence<br />
intervals have no sense.<br />
axesell<br />
a logical value indicating whether the ellipse axes should be drawn<br />
... further arguments passed from the s.label for the initial scatter plot.
s.traject 249<br />
Value<br />
Returns in a hidden way a list of three components :<br />
tra<br />
ell<br />
call<br />
a vector with two values giving the done original translation.<br />
a matrix, with 5 columns and for rows the number of profiles, giving the means,<br />
the variances and the covariance of the profile for the used numerical codes<br />
(column of dfxy)<br />
the matched call<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
par(mfrow = c(2,2))<br />
par(mar = c(0.1,0.1,0.1,0.1))<br />
proba
250 s.traject<br />
Arguments<br />
Value<br />
dfxy<br />
fac<br />
ord<br />
xax<br />
yax<br />
label<br />
clabel<br />
cpoint<br />
pch<br />
xlim<br />
ylim<br />
grid<br />
addaxes<br />
edge<br />
a data frame containing two columns for the axes<br />
a factor partioning the rows of the data frame in classes<br />
a vector of length equal to fac. <strong>The</strong> trajectory is drawn in an ascending order of<br />
the ord values<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
a vector of strings of characters for the point labels<br />
if not NULL, a character size for the labels, used with par("cex")*clabel<br />
a character size for plotting the points, used with par("cex")*cpoint. If<br />
zero, no points are drawn<br />
if cpoint > 0, an integer specifying the symbol or the single character to be<br />
used in plotting points<br />
the ranges to be encompassed by the x, if NULL they are computed<br />
the ranges to be encompassed by the y, if NULL they are computed<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a logical value indicating whether the axes should be plotted<br />
if TRUE the arrows are plotted, otherwhise only the segments<br />
origin the fixed point in the graph space, for example c(0,0) the origin axes<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
sub<br />
csub<br />
possub<br />
cgrid<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
a character size, parameter used with par("cex")*cgrid to indicate the<br />
mesh of the grid<br />
aan object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window
s.value 251<br />
Examples<br />
rw
252 s.value<br />
Value<br />
clegend<br />
neig<br />
cneig<br />
xlim<br />
ylim<br />
grid<br />
addaxes<br />
a character size for the legend used by par("cex")*clegend<br />
a neighbouring graph<br />
a size for the neighbouring graph lines used with par("lwd")*\code{cneig}<br />
the ranges to be encompassed by the x, if NULL they are computed<br />
the ranges to be encompassed by the y, if NULL they are computed<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
a logical value indicating whether the axes should be plotted<br />
cgrid a character size, parameter used with par("cex")*cgrid to indicate the<br />
mesh of the grid<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
origin<br />
sub<br />
csub<br />
possub<br />
pixmap<br />
contour<br />
area<br />
add.plot<br />
<strong>The</strong> matched call.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
the fixed point in the graph space, for example c(0,0) the origin axes<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
an object ’pixmap’ displayed in the map background<br />
a data frame with 4 columns to plot the contour of the map : each row gives a<br />
segment (x1,y1,x2,y2)<br />
a data frame of class ’area’ to plot a set of surface units in contour<br />
if TRUE uses the current graphics window<br />
xy
santacatalina 253<br />
par(mfrow = c(3,4))<br />
irq0
254 sarcelles<br />
sarcelles<br />
Array of Recapture of Rings<br />
Description<br />
<strong>The</strong> data frame sarcelles$tab contains the number of the winter teals (Anas C. Crecca) for<br />
which the ring was retrieved in the area i during the month j (n=3049).<br />
Usage<br />
data(sarcelles)<br />
Format<br />
sarcelles is a list of 4 components.<br />
tab is a data frame with 14 rows-areas and 12 columns-months.<br />
xy is a data frame with the 2 spatial coordinates of the 14 region centers.<br />
neig is the neighbouring graph between areas, object of the class neig.<br />
col.names is a vector containing the month items<br />
<strong>Source</strong><br />
Lebreton, J.D. (1973) Etude des déplacements saisonniers des Sarcelles d’hiver, Anas c. crecca<br />
L., hivernant en Camargue à l’aide de l’analyse factorielle des correspondances. Compte rendu<br />
hebdomadaire des séances de l’Académie des sciences, Paris, D, III, 277, 2417–2420.<br />
Examples<br />
## Not run:<br />
# depends of pixmap<br />
if (require(pixmap, quietly=TRUE)) {<br />
bkgnd.pnm
scalewt 255<br />
scalewt<br />
Centring and Scaling a Matrix of Any Weighting<br />
Description<br />
transforms a numeric matrix in a centred and scaled matrix for any weighting.<br />
Usage<br />
scalewt(X, wt = rep(1, nrow(X)), center = TRUE, scale = TRUE)<br />
Arguments<br />
X<br />
wt<br />
center<br />
scale<br />
a numeric matrix (like object)<br />
a vector of weighting<br />
a logical value indicating whether the array should be centred<br />
a logical value indicating whether the array should be scaled<br />
Value<br />
returns a centred, scaled matrix<br />
Note<br />
<strong>The</strong> norms are calculated with 1/n and the columns of null variance are still equal to zero.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
scalewt(matrix(1:12,4,3))<br />
scale((matrix(1:12,4,3)))<br />
scale(matrix(1,4,3))<br />
scalewt(matrix(1,4,3))
256 scatter<br />
scatter<br />
Scatter Plot<br />
Description<br />
scatter is a generic function. It has methods for the classes coa, dudi, fca, acm and pco.<br />
<strong>The</strong> scale of the grid is situated on the right-top of the graph.<br />
<strong>The</strong> points are in the middle of the labels.<br />
This process plots the graphs of the multivariate analyses.<br />
<strong>The</strong> two axes have the same scale.<br />
Usage<br />
scatter(x, ...)<br />
Arguments<br />
x<br />
an object used to select a method<br />
... further arguments passed to or from other methods<br />
Details<br />
<strong>The</strong> functions scatter use some utilities functions :<br />
scatterutil.base defines the bottom of the plot for all scatters<br />
scatterutil.chull plots the polygons of the external contour<br />
scatterutil.eigen plots the eigenvalues bar plot<br />
scatterutil.ellipse plots an inertia ellipse for a weighting distribution<br />
scatterutil.eti.circ puts labels on a correlation circle<br />
scatterutil.eti puts labels centred on the points<br />
scatterutil.grid plots a grid and adds a legend<br />
scatterutil.legend.bw.square puts a legend of values by square size<br />
scatterutil.legend.square.grey puts a legend by squares and grey levels<br />
scatterutil.legendgris adds a legend of grey levels for the areas<br />
scatterutil.scaling to fit a plot on a background bipmap<br />
scatterutil.star plots a star for a weighting distribution<br />
scatterutil.sub adds a string of characters in sub-title of a graph
scatter 257<br />
Author(s)<br />
See Also<br />
Daniel Chessel<br />
s.arrow, s.chull, s.class, s.corcircle, s.distri, s.label, s.match, s.traject,<br />
s.value, add.scatter<br />
Examples<br />
par(mfrow = c(3,3))<br />
plot.new()<br />
scatterutil.legendgris(1:20, 4, 1.6)<br />
plot.new()<br />
scatterutil.sub("lkn5555555555lkn", csub = 2, possub = "bottomleft")<br />
scatterutil.sub("lkn5555555555lkn", csub = 1, possub = "topleft")<br />
scatterutil.sub("jdjjl", csub = 3, possub = "topright")<br />
scatterutil.sub("**", csub = 2, possub = "bottomright")<br />
x
258 scatter.coa<br />
scatter.acm<br />
Plot of the factorial maps in a Multiple Correspondence Analysis<br />
Description<br />
Usage<br />
performs the scatter diagrams of a Multiple Correspondence Analysis.<br />
## S3 method for class 'acm':<br />
scatter(x, xax = 1, yax = 2, mfrow=NULL, csub = 2, possub = "topleft", ...)<br />
Arguments<br />
x<br />
xax<br />
yax<br />
mfrow<br />
csub<br />
possub<br />
an object of class acm<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
a vector of the form "c(nr,nc)", if NULL (the default) is computed by n2mfrow<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the legend position ("topleft", "topright", "bottomleft",<br />
"bottomright") in a array of figures<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(lascaux)<br />
scatter(dudi.acm(lascaux$ornem, sca = FALSE), csub = 3)<br />
scatter.coa<br />
Plot of the factorial maps for a correspondence analysis<br />
Description<br />
Usage<br />
performs the scatter diagrams of a correspondence analysis.<br />
## S3 method for class 'coa':<br />
scatter(x, xax = 1, yax = 2, method = 1:3, clab.row = 0.75,<br />
clab.col = 1.25, posieig = "top", sub = NULL, csub = 2, ...)
scatter.dudi 259<br />
Arguments<br />
x<br />
xax<br />
yax<br />
an object of class coa<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
method an integer between 1 and 3<br />
1 Rows and columns with the coordinates of lambda variance<br />
2 Rows variance 1 and columns by averaging<br />
3 Columns variance 1 and rows by averaging<br />
clab.row<br />
clab.col<br />
posieig<br />
sub<br />
csub<br />
a character size for the rows<br />
a character size for the columns<br />
if "top" the eigenvalues bar plot is upside,vif "bottom" it is downside, if "none"<br />
no plot<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
References<br />
Oksanen, J. (1987) Problems of joint display of species and site scores in correspondence analysis.<br />
Vegetatio, 72, 51–57.<br />
Examples<br />
data(housetasks)<br />
par(mfrow = c(2,2))<br />
w
260 scatter.dudi<br />
Usage<br />
## S3 method for class 'dudi':<br />
scatter(x, xax = 1, yax = 2, clab.row = 0.75, clab.col = 1,<br />
permute = FALSE, posieig = "top", sub = NULL, ...)<br />
Arguments<br />
x<br />
xax<br />
yax<br />
clab.row<br />
clab.col<br />
permute<br />
posieig<br />
sub<br />
an object of class dudi<br />
the column number for the x-axis<br />
the column number for the y-axis<br />
a character size for the rows<br />
a character size for the columns<br />
if FALSE, the rows are plotted by points and the columns by arrows. If TRUE<br />
it is the opposite.<br />
if "top" the eigenvalues bar plot is upside, if "bottom" it is downside, if "none"<br />
no plot<br />
a string of characters to be inserted as legend<br />
... further arguments passed to or from other methods<br />
Details<br />
scatter.dudi is a factorial map of individuals and the projection of the vectors of the canonical<br />
basis multiplied by a constante of rescaling. In the eigenvalues bar plot,the used axes for the plot<br />
are in black, the other kept axes in grey and the other in white.<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(deug)<br />
scatter(dd1
scatter.fca 261<br />
scatter.fca<br />
Plot of the factorial maps for a fuzzy correspondence analysis<br />
Description<br />
performs the scatter diagrams of a fuzzy correspondence analysis.<br />
Usage<br />
## S3 method for class 'fca':<br />
scatter(x, xax = 1, yax = 2, clab.moda = 1, labels = names(x$tab),<br />
sub = NULL, csub = 2, ...)<br />
Arguments<br />
x<br />
an object of class fca<br />
xax<br />
the column number for the x-axis<br />
yax<br />
the column number for the y-axis<br />
clab.moda the character size to write the modalities<br />
labels a vector of strings of characters for the labels of the modalities<br />
sub<br />
a vector of strings of characters to be inserted as legend in each figure<br />
csub<br />
a character size for the legend, used with par("cex")*csub<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
References<br />
Chevenet, F., Dolédec, S. and Chessel, D. (1994) A fuzzy coding approach for the analysis of<br />
long-term ecological data. Freshwater Biology, 31, 295–309.<br />
Examples<br />
data(coleo)<br />
coleo.fuzzy
262 sco.boxplot<br />
sco.boxplot<br />
Representation of the link between a variable and a set of qualitative<br />
variables<br />
Description<br />
Usage<br />
represents the link between a variable and a set of qualitative variables.<br />
sco.boxplot(score, df, labels = names(df), clabel = 1, xlim = NULL,<br />
grid = TRUE, cgrid = 0.75, include.origin = TRUE, origin = 0,<br />
sub = NULL, csub = 1)<br />
Arguments<br />
score<br />
df<br />
labels<br />
clabel<br />
xlim<br />
grid<br />
a numeric vector<br />
a data frame with only factors<br />
a vector of strings of characters for the labels of variables<br />
if not NULL, a character size for the labels, used with par("cex")*clabel<br />
the ranges to be encompassed by the x axis, if NULL they are computed<br />
a logical value indicating whether the scale vertical lines should be drawn<br />
cgrid a character size, parameter used with par("cex")*cgrid to indicate the<br />
mesh of the scale<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
origin<br />
sub<br />
csub<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
the fixed point in the graph space, for example 0 the origin axis<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
w1
sco.distri 263<br />
banque.acm
264 sco.quant<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
w
score 265<br />
Arguments<br />
score<br />
df<br />
fac<br />
clabel<br />
abline<br />
sub<br />
csub<br />
possub<br />
a numeric vector<br />
a data frame which rows equal to the score length<br />
a factor with the same length than the score<br />
character size for the class labels (if any) used with par("cex")*clabel<br />
a logical value indicating whether a regression line should be added<br />
a vector of strings of characters for the labels of variables<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
w
266 score.acm<br />
include.origin<br />
a logical value indicating whether the point "origin" should be belonged to the<br />
graph space<br />
origin<br />
sub<br />
csub<br />
the fixed point in the graph space, for example 0 the origin axis<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
Details<br />
scoreutil.base is a utility function - not for the user - to define the bottom of the layout of all<br />
score.<br />
Author(s)<br />
Daniel Chessel<br />
See Also<br />
sco.boxplot, sco.distri, sco.quant<br />
Examples<br />
## Not run:<br />
par(mar = c(1,1,1,1))<br />
scoreutil.base (runif(20,3,7), xlim = NULL, grid = TRUE, cgrid = 0.8,<br />
include.origin = TRUE, origin = 0, sub = "Uniform", csub = 1)<br />
## End(Not run)<br />
# returns the value of the user coordinate of the low line.<br />
# <strong>The</strong> user window id defined with c(0,1) in ordinate.<br />
# box()<br />
score.acm<br />
Graphs to study one factor in a Multiple Correspondence Analysis<br />
Description<br />
performs the canonical graph of a Multiple Correspondence Analysis.<br />
Usage<br />
## S3 method for class 'acm':<br />
score(x, xax = 1, which.var = NULL, mfrow = NULL,<br />
sub = names(oritab), csub = 2, possub = "topleft", ...)
score.coa 267<br />
Arguments<br />
x<br />
xax<br />
which.var<br />
mfrow<br />
sub<br />
csub<br />
possub<br />
an object of class acm<br />
the column number for the used axis<br />
the numbers of the kept columns for the analysis, otherwise all columns<br />
a vector of the form "c(nr,nc)", otherwise computed by a special own function<br />
n2mfrow<br />
a vector of strings of characters to be inserted as sub-titles, otherwise the variable<br />
names of the initial array<br />
a character size for the sub-titles<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(banque)<br />
banque.acm 0.2), csub = 3)<br />
score.coa<br />
Reciprocal scaling after a correspondence analysis<br />
Description<br />
Usage<br />
performs the canonical graph of a correspondence analysis.<br />
## S3 method for class 'coa':<br />
score(x, xax = 1, dotchart = FALSE, clab.r = 1, clab.c = 1,<br />
csub = 1, cpoi = 1.5, cet = 1.5, ...)<br />
reciprocal.coa(x)<br />
Arguments<br />
x<br />
xax<br />
dotchart<br />
clab.r<br />
clab.c<br />
an object of class coa<br />
the column number for the used axis<br />
if TRUE the graph gives a "dual scaling", if FALSE a "reciprocal scaling"<br />
a character size for row labels<br />
a character size for column labels
268 score.coa<br />
csub<br />
cpoi<br />
cet<br />
Details<br />
Value<br />
a character size for the sub-titles, used with par("cex")*csub<br />
a character size for the points<br />
a coefficient for the size of segments in standard deviation<br />
... further arguments passed to or from other methods<br />
In a "reciprocal scaling", the reference score is a numeric code centred and normalized of the non<br />
zero cells of the array which both maximizes the variance of means by row and by column. <strong>The</strong><br />
bars are drawn with half the length of this standard deviation.<br />
return a data.frame with the scores, weights and factors of correspondences (non zero cells)<br />
Author(s)<br />
Daniel Chessel<br />
References<br />
Thioulouse, J. and Chessel D. (1992) A method for reciprocal scaling of species tolerance and<br />
sample diversity. Ecology, 73, 670–680.<br />
Examples<br />
layout(matrix(c(1,1,2,3), 2, 2), resp = FALSE)<br />
data(aviurba)<br />
dd1 averaging -> species amplitude<br />
# 3 species score -> averaging -> sample diversity<br />
layout(matrix(c(1,1,2,3), 2, 2), resp = FALSE)<br />
data(rpjdl)<br />
rpjdl1
score.mix 269<br />
par(mfrow = c(1,1))<br />
score(rpjdl1, dotchart = TRUE, clab.r = 0)<br />
score.mix<br />
Graphs to Analyse a factor in a Mixed Analysis<br />
Description<br />
performs the canonical graph of a mixed analysis.<br />
Usage<br />
## S3 method for class 'mix':<br />
score(x, xax = 1, csub = 2, mfrow = NULL, which.var = NULL, ...)<br />
Arguments<br />
x<br />
xax<br />
csub<br />
mfrow<br />
which.var<br />
an object of class mix<br />
the column number for the used axis<br />
a character size for the sub-titles, used with par("cex")*csub<br />
a vector of the form "c(nr,nc)", otherwise computed by a special own function<br />
n2mfrow<br />
the numbers of the kept columns for the analysis, otherwise all columns<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(lascaux)<br />
w
270 score.pca<br />
score.pca<br />
Graphs to Analyse a factor in PCA<br />
Description<br />
performs the canonical graph of a Principal Component Analysis.<br />
Usage<br />
## S3 method for class 'pca':<br />
score(x, xax = 1, which.var = NULL, mfrow = NULL, csub = 2,<br />
sub = names(x$tab), abline = TRUE, ...)<br />
Arguments<br />
x<br />
xax<br />
which.var<br />
mfrow<br />
csub<br />
sub<br />
abline<br />
an object of class pca<br />
the column number for the used axis<br />
the numbers of the kept columns for the analysis, otherwise all columns<br />
a vector of the form "c(nr,nc)", otherwise computed by a special own function<br />
n2mfrow<br />
a character size for sub-titles, used with par("cex")*csub<br />
a vector of string of characters to be inserted as sub-titles, otherwise the names<br />
of the variables<br />
a logical value indicating whether a regression line should be added<br />
... further arguments passed to or from other methods<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(deug)<br />
dd1
seconde 271<br />
seconde<br />
Students and Subjects<br />
Description<br />
<strong>The</strong> seconde data frame gives the marks of 22 students for 8 subjects.<br />
Usage<br />
data(seconde)<br />
Format<br />
This data frame (22,8) contains the following columns: - HGEO: History and Geography - FRAN:<br />
French literature - PHYS: Physics - MATH: Mathematics - BIOL: Biology - ECON: Economy -<br />
ANGL: English language - ESPA: Spanish language<br />
<strong>Source</strong><br />
Personal communication<br />
Examples<br />
data(seconde)<br />
scatter(dudi.pca(seconde, scan = FALSE), clab.r = 1, clab.c = 1.5)<br />
sepan<br />
Separated Analyses in a K-tables<br />
Description<br />
performs K separated multivariate analyses of an object of class ktab containing K tables.<br />
Usage<br />
sepan(X, nf = 2)<br />
## S3 method for class 'sepan':<br />
plot(x, mfrow = NULL, csub = 2, ...)<br />
## S3 method for class 'sepan':<br />
summary(object, ...)<br />
## S3 method for class 'sepan':<br />
print(x, ...)
272 sepan<br />
Arguments<br />
X<br />
nf<br />
Details<br />
Value<br />
an object of class ktab<br />
an integer indicating the number of kept axes for each separated analysis<br />
x, object an object of class ’sepan’<br />
mfrow<br />
csub<br />
a vector of the form "c(nr,nc)", otherwise computed by a special own function<br />
n2mfrow<br />
a character size for the sub-titles, used with par("cex")*csub<br />
... further arguments passed to or from other methods<br />
<strong>The</strong> function plot on a sepan object allows to compare inertias and structures between arrays. In<br />
black, the eigenvalues of kept axes in the object ’sepan’.<br />
returns a list of class ’sepan’ containing :<br />
call<br />
tab.names<br />
blo<br />
rank<br />
Eig<br />
Li<br />
L1<br />
Co<br />
C1<br />
TL<br />
TC<br />
a call order<br />
a vector of characters with the names of tables<br />
a numeric vector with the numbers of columns for each table<br />
a numeric vector with the rank of the studied matrix for each table<br />
a numeric vector with all the eigenvalues<br />
a data frame with the row coordinates<br />
a data frame with the row normed scores<br />
a data frame with the column coordinates<br />
a data frame with the column normed coordinates<br />
a data frame with the factors for Li L1<br />
a data frame with the factors for Co C1<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(escopage)<br />
w
skulls 273<br />
skulls<br />
Morphometric Evolution<br />
Description<br />
Usage<br />
Format<br />
Details<br />
This data set gives four anthropometric measures of 150 Egyptean skulls belonging to five different<br />
historical periods.<br />
data(skulls)<br />
<strong>The</strong> skulls data frame has 150 rows (egyptean skulls) and 4 columns (anthropometric measures).<br />
<strong>The</strong> four variables are the maximum breadth (V1), the basibregmatic height (V2), the basialveolar<br />
length (V3) and the nasal height (V4). All measurements were taken in millimeters.<br />
<strong>The</strong> measurements are made on 5 groups and 30 Egyptian skulls. <strong>The</strong> groups are defined as follows<br />
:<br />
1 - the early predynastic period (circa 4000 BC)<br />
2 - the late predynastic period (circa 3300 BC)<br />
3 - the 12th and 13th dynasties (circa 1850 BC)<br />
4 - the Ptolemiac period (circa 200 BC)<br />
5 - the Roman period (circa 150 BC)<br />
<strong>Source</strong><br />
Thompson, A. and Randall-Maciver, R. (1905) Ancient races of the <strong>The</strong>baid, Oxford University<br />
Press.<br />
References<br />
Manly, B.F. (1994) Multivariate Statistical Methods. A primer, Second edition. Chapman & Hall,<br />
London. 1–215.<br />
<strong>The</strong> example is treated pp. 6, 13, 51, 64, 72, 107, 112 and 117.<br />
Examples<br />
data(skulls)<br />
pca1
274 statis<br />
statis<br />
STATIS, a method for analysing K-tables<br />
Description<br />
Usage<br />
performs a STATIS analysis of a ktab object.<br />
statis(X, scannf = TRUE, nf = 3, tol = 1e-07)<br />
## S3 method for class 'statis':<br />
plot(x, xax = 1, yax = 2, option = 1:4, ...)<br />
## S3 method for class 'statis':<br />
print(x, ...)<br />
Arguments<br />
X<br />
scannf<br />
nf<br />
tol<br />
x<br />
Value<br />
xax, yax<br />
option<br />
an object of class ’ktab’<br />
a logical value indicating whether the number of kept axes for the compromise<br />
should be asked<br />
if scannf FALSE, an integer indicating the number of kept axes for the compromise<br />
a tolerance threshold to test whether the distance matrix is Euclidean : an eigenvalue<br />
is considered positive if it is larger than -tol*lambda1 where lambda1<br />
is the largest eigenvalue<br />
an object of class ’statis’<br />
the numbers of the x-axis and the y-axis<br />
an integer between 1 and 4, otherwise the 4 components of the plot are dispayed<br />
... further arguments passed to or from other methods<br />
statis returns a list of class ’statis’ containing :<br />
$RV<br />
RV.eig<br />
RV.coo<br />
tab.names<br />
$RV.tabw<br />
nf<br />
rank<br />
C.li<br />
C.Co<br />
a matrix with the all RV coefficients<br />
a numeric vector with all the eigenvalues<br />
a data frame with the array scores<br />
a vector of characters with the names of the arrays<br />
a numeric vector with the array weigths<br />
an integer indicating the number of kept axes<br />
an integer indicating the rank of the studied matrix<br />
a data frame with the row coordinates<br />
a data frame with the column coordinates
steppe 275<br />
C.T4<br />
TL<br />
TC<br />
T4<br />
a data frame with the principal vectors (for each table)<br />
a data frame with the factors (not used)<br />
a data frame with the factors for Co<br />
a data frame with the factors for T4<br />
Author(s)<br />
Daniel Chessel<br />
References<br />
Lavit, C. (1988) Analyse conjointe de tableaux quantitatifs, Masson, Paris.<br />
Lavit, C., Escoufier, Y., Sabatier, R. and Traissac, P. (1994) <strong>The</strong> ACT (Statis method). Computational<br />
Statistics and Data Analysis, 18, 97–119.<br />
Examples<br />
data(jv73)<br />
kta1
276 supcol<br />
Format<br />
<strong>Source</strong><br />
steppe is a list of 2 components.<br />
tab is a data frame with 512 rows (sites) and 37 variables (species) in presence-absence.<br />
esp.names is a vector of the species names.<br />
Estève, J. (1978) Les méthodes d’ordination : éléments pour une discussion. in J. M. Legay and R.<br />
Tomassone, editors. Biométrie et Ecologie, Société Française de Biométrie, Paris, 223–250.<br />
Examples<br />
par(mfrow = c(3,1))<br />
data(steppe)<br />
w1
suprow 277<br />
Details<br />
If supcol.default is used, the column vectors of Xsup are projected without prior modification<br />
onto the principal components of dudi with the scalar product associated to the row weightings<br />
of dudi.<br />
Value<br />
returns a list of two components : $tabsup data frame containing the array with the supplementary<br />
columns transformed or not $cosup data frame containing the coordinates of the supplementary<br />
projections<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
Examples<br />
data(rpjdl)<br />
rpjdl.coa
278 suprow<br />
Arguments<br />
x<br />
Details<br />
Value<br />
Xsup<br />
an object of class dudi<br />
an array with the supplementary rows (Xsup and x$tab have the same column<br />
number)<br />
... further arguments passed to or from other methods<br />
If suprow.default is used, the column vectors of Xsup are projected without prior modifications<br />
onto the principal components of dudi with the scalar product associated to the row weightings<br />
of dudi.<br />
returns a data frame containing the coordinates of the supplementary projections<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Gower, J. C. (1967) Multivariate analysis and multivariate geometry. <strong>The</strong> statistician, 17, 13–28.<br />
Examples<br />
data(euro123)<br />
par(mfrow = c(2,2))<br />
w
symbols.phylog 279<br />
symbols.phylog<br />
Representation of a quantitative variable in front of a phylogenetic<br />
tree<br />
Description<br />
symbols.phylog draws the phylogenetic tree and represents the values of the variable by symbols<br />
(squares or circles) which size is proportional to value. White symbols correspond to values<br />
which are below the mean, and black symbols correspond to values which are over.<br />
Usage<br />
symbols.phylog(phylog, circles, squares, csize = 1, clegend = 1,<br />
sub = "", csub = 1, possub = "topleft")<br />
Arguments<br />
phylog<br />
circles<br />
squares<br />
csize<br />
clegend<br />
sub<br />
csub<br />
possub<br />
an object of class phylog<br />
a vector giving the radii of the circles<br />
a vector giving the length of the sides of the squares<br />
a size coefficient for symbols<br />
a character size for the legend used by par("cex")*clegend<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
Author(s)<br />
Daniel Chessel<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
See Also<br />
table.phylog and dotchart.phylog for many variables<br />
Examples<br />
data(mjrochet)<br />
mjrochet.phy
280 t3012<br />
syndicats<br />
Two Questions asked on a Sample of 1000 Respondents<br />
Description<br />
This data set is extracted from an opinion poll (period 1970-1980) on 1000 respondents.<br />
Usage<br />
data(syndicats)<br />
Format<br />
<strong>The</strong> syndicats data frame has 5 rows and 4 columns.<br />
"Which politic family are you agreeing about ?" has 5 response items : extgauche (extreme left)<br />
left center right and extdroite (extreme right)<br />
"What do you think of the trade importance ?" has 4 response items : trop (too important)<br />
adequate insufficient nesaispas (no opinion)<br />
<strong>Source</strong><br />
unknown<br />
Examples<br />
data(syndicats)<br />
par(mfrow = c(1,2))<br />
dudi1
table.cont 281<br />
Format<br />
<strong>Source</strong><br />
t3012 is a list of 3 objects:<br />
xy is a data frame with 30 rows (cities) and 2 coordinates (x,y).<br />
temp is a data frame with 30 rows (cities) and 12 columns (months). Each column contains the<br />
average temperature in tenth of degree Celsius.<br />
contour is a data frame with 4 columns (x1,y1,x2,y2) for the contour display of France.<br />
Besse, P. (1979) Etude descriptive d’un processus; approximation, interpolation. Thèse de troisième<br />
cycle, Université Paul Sabatier, Toulouse.<br />
Examples<br />
data(t3012)<br />
data(elec88)<br />
area.plot(elec88$area)<br />
s.arrow(t3012$xy, ori = as.numeric(t3012$xy["Paris",]),<br />
add.p = TRUE)<br />
table.cont<br />
Plot of Contingency Tables<br />
Description<br />
presents a graph for viewing contingency tables.<br />
Usage<br />
table.cont(df, x = 1:ncol(df), y = 1:nrow(df),<br />
row.labels = row.names(df), col.labels = names(df),<br />
clabel.row = 1, clabel.col = 1, abmean.x = FALSE, abline.x = FALSE,<br />
abmean.y = FALSE, abline.y = FALSE, csize = 1, clegend = 0, grid = TRUE)<br />
Arguments<br />
df<br />
x<br />
y<br />
row.labels<br />
col.labels<br />
clabel.row<br />
clabel.col<br />
a data frame with only positive or null values<br />
a vector of values to position the columns<br />
a vector of values to position the rows<br />
a character vector for the row labels<br />
a character vetor for the column labels<br />
a character size for the row labels<br />
a character size for the column labels
282 table.dist<br />
abmean.x<br />
abline.x<br />
abmean.y<br />
abline.y<br />
csize<br />
clegend<br />
grid<br />
a logical value indicating whether the column conditional means should be<br />
drawn<br />
a logical value indicating whether the regression line of y onto x should be plotted<br />
a logical value indicating whether the row conditional means should be drawn<br />
a logical value indicating whether the regression line of x onto y should be plotted<br />
a coefficient for the square size of the values<br />
if not NULL, a character size for the legend used with par("cex")*clegend<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(chats)<br />
chatsw
table.paint 283<br />
Usage<br />
table.dist(d, x = 1:(attr(d, "Size")), labels = as.character(x),<br />
clabel = 1, csize = 1, grid = TRUE)<br />
Arguments<br />
d<br />
x<br />
labels<br />
clabel<br />
csize<br />
grid<br />
an object of class dist<br />
a vector of the row and column positions<br />
a vector of strings of characters for the labels<br />
a character size for the labels<br />
a coefficient for the circle size<br />
a logical value indicating whether a grid in the background of the plot should be<br />
drawn<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(eurodist)<br />
table.dist(eurodist, labels = attr(eurodist, "Labels"))<br />
table.paint<br />
Plot of the arrays by grey levels<br />
Description<br />
presents a graph for viewing the numbers of a table by grey levels.<br />
Usage<br />
table.paint(df, x = 1:ncol(df), y = nrow(df):1,<br />
row.labels = row.names(df), col.labels = names(df),<br />
clabel.row = 1, clabel.col = 1, csize = 1, clegend = 1)<br />
Arguments<br />
df<br />
x<br />
y<br />
row.labels<br />
col.labels<br />
clabel.row<br />
clabel.col<br />
csize<br />
clegend<br />
a data frame<br />
a vector of values to position the columns, used only for the ordered values<br />
a vector of values to position the rows, used only for the ordered values<br />
a character vector for the row labels<br />
a character vector for the column labels<br />
a character size for the row labels<br />
a character size for the column labels<br />
if ’clegend’ not NULL, a coefficient for the legend size<br />
a character size for the legend, otherwise no legend
284 table.phylog<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(rpjdl)<br />
X
table.value 285<br />
labels.col<br />
clabel.col<br />
labels.nod<br />
clabel.nod<br />
cleaves<br />
cnodes<br />
csize<br />
grid<br />
clegend<br />
: a vector of strings of characters for columns labels<br />
: a character size for the leaves labels, used with par("cex")*clabel.col.<br />
If zero, no column labels are drawn<br />
: a vector of strings of characters for the nodes labels<br />
: a character size for the nodes labels, used with par("cex")*clabel.nodes.<br />
If zero, no nodes labels are drawn<br />
: a character size for plotting the points that represent the leaves, used with<br />
par("cex")*cleaves. If zero, no points are drawn<br />
: a character size for plotting the points that represent the nodes, used with<br />
par("cex")*cnodes. If zero, no points are drawn<br />
: a size coefficient for symbols<br />
: a logical value indicating whether the grid should be plotted<br />
: a character size for the legend (if 0, no legend)<br />
Details<br />
<strong>The</strong> function verifies that sort(row.names(df))==sort(names(phylog$leaves)). If<br />
df is a matrix the function uses as.data.frame(df).<br />
Author(s)<br />
Daniel Chessel<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
See Also<br />
symbols.phylog for one variable<br />
Examples<br />
data(newick.eg)<br />
w.phy
286 tarentaise<br />
Usage<br />
table.value(df, x = 1:ncol(df), y = nrow(df):1,<br />
row.labels = row.names(df), col.labels = names(df), clabel.row = 1,<br />
clabel.col = 1, csize = 1, clegend = 1, grid = TRUE)<br />
Arguments<br />
df<br />
x<br />
y<br />
row.labels<br />
col.labels<br />
clabel.row<br />
clabel.col<br />
csize<br />
clegend<br />
grid<br />
a data frame<br />
a vector of values to position the columns<br />
a vector of values to position the rows<br />
a character vector for the row labels<br />
a character vector for the column labels<br />
a character size for the row labels<br />
a character size for the column labels<br />
a coefficient for the square size of the values<br />
a character size for the legend (if 0, no legend)<br />
a logical value indicating whether the grid should be plotted<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
data(olympic)<br />
w
tarentaise 287<br />
Format<br />
tarentaise is a list of 5 components.<br />
ecol is a data frame with 376 sites and 98 bird species.<br />
frnames is a vector of the 98 French names of the species.<br />
alti is a vector giving the altitude of the 376 sites in m.<br />
envir is a data frame with 14 environmental variables.<br />
traits is a data frame with 29 biological variables of the 98 species.<br />
Details<br />
<strong>The</strong> attribute col.blocks of the data frame tarentaise$traits indicates it is composed of<br />
6 units of variables.<br />
<strong>Source</strong><br />
Original data from Hubert Tournier, University of Savoie and Philippe Lebreton, University of Lyon<br />
1.<br />
References<br />
Lebreton, P., Tournier H. and Lebreton J. D. (1976) Etude de l’avifaune du Parc National de la<br />
Vanoise VI Recherches d’ordre quantitatif sur les Oiseaux forestiers de Vanoise. Travaux Scientifiques<br />
du parc National de la vanoise, 7, 163–243.<br />
Lebreton, Ph. and Martinot, J.P. (1998) Oiseaux de Vanoise. Guide de l’ornithologue en montagne.<br />
Libris, Grenoble. 1–240.<br />
Lebreton, Ph., Lebrun, Ph., Martinot, J.P., Miquet, A. and Tournier, H. (1999) Approche écologique<br />
de l’avifaune de la Vanoise. Travaux scientifiques du Parc national de la Vanoise, 21, 7–304.<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps038.pdf (in French).<br />
Examples<br />
data(tarentaise)<br />
coa1
288 taxo.eg<br />
taxo.eg<br />
Examples of taxonomy<br />
Description<br />
This data sets contains two taxonomies.<br />
Usage<br />
data(taxo.eg)<br />
Format<br />
taxo.eg is a list containing the 2 following objects:<br />
taxo.eg[[1 ]] is a data frame with 15 species and 3 columns.<br />
taxo.eg[[2 ]] is a data frame with 40 species and 2 columns.<br />
Details<br />
Variables of the first data frame are : genre (a factor genre with 8 levels), famille (a factor familiy<br />
with 5 levels) and ordre (a factor order with 2 levels).<br />
Variables of the second data frame are : gen(a factor genre with 29 levels), fam (a factor family with<br />
19 levels).<br />
Examples<br />
data(taxo.eg)<br />
taxo.eg[[1]]<br />
as.taxo(taxo.eg[[1]])<br />
class(taxo.eg[[1]])<br />
class(as.taxo(taxo.eg[[1]]))<br />
tax.phy
testdim 289<br />
testdim<br />
Function to perform a test of dimensionality<br />
Description<br />
This functions allow to test for the number of axes in multivariate analysis. <strong>The</strong> procedure is only<br />
implemented for principal component analysis on correlation matrix. <strong>The</strong> procedure is based on the<br />
computation of the RV coefficient.<br />
Usage<br />
testdim(dudi, ...)<br />
## S3 method for class 'pca':<br />
testdim(dudi, nrepet = 99, nbax = dudi$rank, alpha = 0.05, ...)<br />
Arguments<br />
dudi<br />
a duality diagram (an object of class dudi)<br />
nrepet the number of repetitions for the permutation procedure<br />
nbax<br />
the number of axes to be tested, by default all axes<br />
alpha the significance level<br />
... other arguments<br />
Value<br />
An object of the class krandtest. It contains also:<br />
nb<br />
nb.cor<br />
<strong>The</strong> estimated number of axes to keep<br />
<strong>The</strong> number of axes to keep estimated using a sequential Bonferroni procedure<br />
Author(s)<br />
Stephane Dray 〈dray@biomserv.univ-lyon1.fr〉<br />
References<br />
Dray, S. (2007) On the number of principal components: A test of dimensionality based on measurements<br />
of similarity between matrices. Computational Statistics and Data Analysis, in press.<br />
See Also<br />
dudi.pca, RV.rtest
290 tintoodiel<br />
Examples<br />
tab
tithonia 291<br />
s.label(tintoodiel$xy,pixmap = estuary.pnm, neig = tintoodiel$neig,<br />
clab = 0, cpoi = 2, cneig = 3, addax = FALSE, cgrid = 0, grid = FALSE)<br />
}<br />
## End(Not run)<br />
estuary.pca
292 tortues<br />
demo11: is a numeric vector that describes the viability (per cent)<br />
demo12: is a numeric vector that describes the germination (per cent)<br />
demo13: is a integer vector that describes the resource allocation<br />
demo14: is a numeric vector that describes the adult height (m)<br />
<strong>Source</strong><br />
Data were obtained from Morales, E. (2000) Estimating phylogenetic inertia in Tithonia (Asteraceae)<br />
: a comparative approach. Evolution, 54, 2, 475–484.<br />
Examples<br />
data(tithonia)<br />
phy
toxicity 293<br />
points(ref,xyz[,2], pch = pch0)<br />
abline(lm(xyz[,2]~ -1 + ref))<br />
points(ref,xyz[,3], pch = pch0)<br />
abline(lm(xyz[,3]~ -1 + ref))<br />
toxicity<br />
Homogeneous Table<br />
Description<br />
This data set gives the toxicity of 7 molecules on 16 targets expressed in -log(mol/liter)<br />
Usage<br />
data(toxicity)<br />
Format<br />
toxicity is a list of 3 components.<br />
tab is a data frame with 7 columns and 16 rows<br />
species is a vector of the names of the species in the 16 targets<br />
chemicals is a vector of the names of the 7 molecules<br />
<strong>Source</strong><br />
Devillers, J., Thioulouse, J. and Karcher W. (1993) Chemometrical Evaluation of Multispecies-<br />
Multichemical Data by Means of Graphical Techniques Combined with Multivariate Analyses.<br />
Ecotoxicology and Environnemental Safety, 26, 333–345.<br />
Examples<br />
data(toxicity)<br />
table.paint(toxicity$tab, row.lab = toxicity$species,<br />
col.lab = toxicity$chemicals)<br />
table.value(toxicity$tab, row.lab = toxicity$species,<br />
col.lab = toxicity$chemicals)
294 triangle.class<br />
triangle.class<br />
Triangular Representation and Groups of points<br />
Description<br />
Usage<br />
A concise (1-5 lines) description of what the function does.<br />
triangle.class(ta, fac, col = rep(1, length(levels(fac))),<br />
wt = rep(1, length(fac)), cstar = 1, cellipse = 0, axesell = TRUE,<br />
label = levels(fac), clabel = 1, cpoint = 1, pch = 20, draw.line = TRUE,<br />
addaxes = FALSE, addmean = FALSE, labeltriangle = TRUE, sub = "", csub = 1,<br />
possub = "bottomright", show.position = TRUE, scale = TRUE, min3 = NULL,<br />
max3 = NULL)<br />
Arguments<br />
ta<br />
fac<br />
col<br />
wt<br />
cstar<br />
cellipse<br />
axesell<br />
label<br />
clabel<br />
cpoint<br />
pch<br />
draw.line<br />
addaxes<br />
a data frame with 3 columns of null or positive numbers<br />
a factor of length the row number of ta<br />
a vector of color for showing the groups<br />
a vector of row weighting for the computation of the gravity centers by class<br />
a character size for plotting the stars between 0 (no stars) and 1 (complete star)<br />
for a line linking a point to the gravity center of its belonging class.<br />
a positive coefficient for the inertia ellipse size<br />
a logical value indicating whether the ellipse axes should be drawn<br />
a vector of strings of characters for the labels of gravity centers<br />
if not NULL, a character size for the labels, used with par("cex")*clabel<br />
a character size for plotting the points, used with par("cex")*cpoint. If<br />
zero, no points are drawn<br />
if cpoint > 0, an integer specifying the symbol or the single character to be<br />
used in plotting points<br />
a logical value indicating whether the triangular lines should be drawn<br />
a logical value indicating whether the axes should be plotted<br />
addmean a logical value indicating whether the mean point should be plotted<br />
labeltriangle<br />
a logical value indicating whether the varliable labels of ta should be drawn on<br />
the triangular sides<br />
sub<br />
csub<br />
possub<br />
a string of characters for the graph title<br />
a character size for plotting the graph title<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")
triangle.plot 295<br />
show.position<br />
a logical value indicating whether the sub-triangle containing the data should be<br />
put back in the total triangle<br />
scale<br />
a logical value for the graph representation : the total triangle (FALSE) or the<br />
sub-triangle (TRUE)<br />
min3 if not NULL, a vector with 3 numbers between 0 and 1<br />
max3<br />
Author(s)<br />
Daniel Chessel<br />
Examples<br />
if not NULL, a vector with 3 numbers between 0 and 1. Let notice that min3+max3<br />
must equal c(1,1,1)<br />
data(euro123)<br />
par(mfrow = c(2,2))<br />
x = rbind.data.frame(euro123$in78, euro123$in86, euro123$in97)<br />
triangle.plot(x)<br />
triangle.class(x, as.factor(rep("G",36)), csta = 0.5, cell = 1)<br />
triangle.class(x, euro123$plan$an)<br />
triangle.class(x, euro123$plan$pays)<br />
triangle.class(x, euro123$plan$an, cell = 1, axesell = TRUE)<br />
triangle.class(x, euro123$plan$an, cell = 0, csta = 0,<br />
col = c("red", "green", "blue"), axesell = TRUE, clab = 2, cpoi = 2)<br />
triangle.class(x, euro123$plan$an, cell = 2, csta = 0.5,<br />
axesell = TRUE, clab = 1.5)<br />
triangle.class(x, euro123$plan$an, cell = 0, csta = 1, scale = FALSE,<br />
draw.line = FALSE, show.posi = FALSE)<br />
triangle.plot<br />
Triangular Plotting<br />
Description<br />
Usage<br />
Graphs for a dataframe with 3 columns of positive or null values<br />
triangle.plot is a scatterplot<br />
triangle.biplot is a paired scatterplots<br />
triangle.posipoint, triangle.param, add.position.triangle are utilitaries functions.<br />
triangle.plot(ta, label = as.character(1:nrow(ta)), clabel = 0,<br />
cpoint = 1, draw.line = TRUE, addaxes = FALSE, addmean = FALSE,<br />
labeltriangle = TRUE, sub = "", csub = 0, possub = "topright",<br />
show.position = TRUE, scale = TRUE, min3 = NULL, max3 = NULL,
296 triangle.plot<br />
box = FALSE)<br />
triangle.biplot (ta1, ta2, label = as.character(1:nrow(ta1)),<br />
draw.line = TRUE, show.position = TRUE, scale = TRUE)<br />
Arguments<br />
ta, ta1, ta2,<br />
data frame with three columns, will be transformed in percentages by rows<br />
label<br />
clabel<br />
cpoint<br />
draw.line<br />
addaxes<br />
addmean<br />
a vector of strings of characters for the point labels<br />
if not NULL, a character size for the labels, used with par("cex")*clabel<br />
a character size for plotting the points, used with par("cex")*cpoint. If<br />
zero, no points are drawn<br />
a logical value indicating whether the lines into the triangle should be drawn<br />
a logical value indicating whether the principal axes should be drawn<br />
a logical value indicating whether the mean should be plotted<br />
labeltriangle<br />
a logical value indicating whether the variable names should be wrote<br />
sub<br />
csub<br />
possub<br />
a string of characters to be inserted as legend<br />
a character size for the legend, used with par("cex")*csub<br />
a string of characters indicating the sub-title position ("topleft", "topright", "bottomleft",<br />
"bottomright")<br />
show.position<br />
a logical value indicating whether the used triangle should be shown in the complete<br />
one<br />
scale<br />
min3<br />
max3<br />
box<br />
a logical value indicating whether the smaller equilateral triangle containing the<br />
plot should be used<br />
If scale is FALSE, a vector of three values for the minima e.g. c(0.1,0.1,0.1) can<br />
be used<br />
If scale is FALSE a vector of three values for the maxima e.g. c(0.9,0.9,0.9) can<br />
be used<br />
a logical value indicating whether a box around the current plot should be drawn<br />
Value<br />
triangle.plot returns an invisible matrix containing the coordinates used for the plot. <strong>The</strong><br />
graph can be supplemented in various ways.<br />
Author(s)<br />
Daniel Chessel
trichometeo 297<br />
Examples<br />
data (euro123)<br />
tot
298 ungulates<br />
<strong>Source</strong><br />
Data from P. Usseglio-Polatera<br />
References<br />
Usseglio-Polatera, P. and Auda, Y. (1987) Influence des facteurs météorologiques sur les résultats<br />
de piégeage lumineux. Annales de Limnologie, 23, 65–79. (code des espèces p. 76)<br />
See a data description at http://pbil.univ-lyon1.fr/R/pps/pps034.pdf (in French).<br />
Examples<br />
data(trichometeo)<br />
faulog
uniquewt.df 299<br />
<strong>Source</strong><br />
Data were obtained from Pélabon, C., Gaillard, J.M., Loison, A. and Portier, A. (1995) Is sex-biased<br />
maternal care limited by total maternal expenditure in polygynous ungulates? Behavioral Ecology<br />
and Sociobiology, 37, 311–319.<br />
Examples<br />
data(ungulates)<br />
ung.phy
300 variance.phylog<br />
Examples<br />
data(ecomor)<br />
forsub.r
vegtf 301<br />
Value<br />
Returns a list containing<br />
lm : an object of class lm that corresponds to the linear regression of z on A.<br />
anova : an object of class anova that corresponds to the anova of the precedent model.<br />
smry<br />
: an object of class table that is a summary of the precedent object.<br />
Author(s)<br />
Sébastien Ollier 〈ollier@biomserv.univ-lyon1.fr〉<br />
Daniel Chessel<br />
References<br />
Grafen, A. (1989) <strong>The</strong> phylogenetic regression. Philosophical Transactions of the Royal Society<br />
London B, 326, 119–156.<br />
Diniz-Filho, J. A. F., Sant’Ana, C.E.R. and Bini, L.M. (1998) An eigenvector method for estimating<br />
phylogenetic inertia. Evolution, 52, 1247–1262.<br />
See Also<br />
phylog, lm<br />
Examples<br />
data(njplot)<br />
njplot.phy
302 veuvage<br />
Format<br />
<strong>Source</strong><br />
vegtf is a list containing the following objects :<br />
veg is a data.frame with the abundance values of 80 species (columns) in 337 sites (rows).<br />
xy is a data.frame with the spatial coordinates of the sites.<br />
area is data.frame (area) which define the boundaries of the study site.<br />
nb is a neighborhood object (class nb defined in package spdep)<br />
Dray, S., Said, S. and Debias, F. (2007) Spatial ordination of vegetation data using a generalization<br />
of Wartenberg’s multivariate spatial correlation. Journal of vegetation science. in press.<br />
Examples<br />
if (require(spdep, quiet=TRUE)){<br />
data(vegtf)<br />
coa1
westafrica 303<br />
Details<br />
<strong>The</strong> columns contain the socioprofessional categories:<br />
1- Farmers, 2- Craftsmen, 3- Executives and higher intellectual professions,<br />
4- Intermediate Professions, 5- Others white-collar workers and 6- Manual workers.<br />
<strong>Source</strong><br />
unknown<br />
Examples<br />
data(veuvage)<br />
par(mfrow = c(3,2))<br />
for (j in 1:6) plot(veuvage$age, veuvage$tab[,j],<br />
xlab = "âge", ylab = "pourcentage de veufs",<br />
type = "b", main = names(veuvage$tab)[j])<br />
westafrica<br />
Freshwater fish zoogeography in west Africa<br />
Description<br />
This data set contains informations about faunal similarities between river basins in West africa.<br />
Usage<br />
data(westafrica)<br />
Format<br />
westafrica is a list containing the following objects :<br />
tab : a data frame with absence/presence of 268 species (rows) at 33 embouchures (columns)<br />
spe.names : a vector of string of characters with the name of species<br />
spe.binames : a data frame with the genus and species (columns) of the 256 species (rows)<br />
riv.names : a vector of string of characters with the name of rivers<br />
atlantic : a data frame with the coordinates of a polygon that represents the limits of atlantic (see<br />
example)<br />
riv.xy : a data frame with the coordinates of embouchures<br />
lines : a data frame with the coordinates of lines to complete the representation (see example)<br />
cadre : a data frame with the coordinates of points used to make the representation (see example)
304 westafrica<br />
<strong>Source</strong><br />
Data provided by B. Hugueny 〈hugueny@biomserv.univ-lyon1.fr〉.<br />
Paugy, D., Traoré, K. and Diouf, P.F. (1994) Faune ichtyologique des eaux douces d’Afrique de<br />
l’Ouest. In Diversité biologique des poissons des eaux douces et saumâtres d’Afrique. Synthèses<br />
géographiques, Teugels, G.G., Guégan, J.F. and Albaret, J.J. (Editors). Annales du Musée Royal de<br />
l’Afrique Centrale, Zoologie, 275, Tervuren, Belgique, 35–66.<br />
Hugueny, B. (1989) Biogéographie et structure des peuplements de Poissons d’eau douce de l’Afrique<br />
de l’ouest : approches quantitatives. Thèse de doctorat, Université Paris 7.<br />
References<br />
Hugueny, B., and Lévêque, C. (1994) Freshwater fish zoogeography in west Africa: faunal similarities<br />
between river basins. Environmental Biology of Fishes, 39, 365–380.<br />
Examples<br />
data(westafrica)<br />
s.label(westafrica$cadre, xlim = c(30,500), ylim = c(50,290),<br />
cpoi = 0, clab = 0, grid = FALSE, addax = 0)<br />
old.par
within 305<br />
afri.ms
306 within<br />
Value<br />
Returns a list of the sub-class within in the class dudi<br />
call<br />
origine<br />
nf<br />
number of axis saved<br />
rank<br />
rank<br />
ratio percentage of within inertia<br />
eig<br />
numeric eigen values<br />
lw<br />
numeric row weigths<br />
cw<br />
numeric col weigths<br />
tabw<br />
numeric table weigths<br />
fac<br />
factor for grouping<br />
tab<br />
data frame class-variables<br />
li<br />
data frame row coordinates<br />
l1<br />
data frame row normed scores<br />
co<br />
data frame column coordinates<br />
$c1 data frame column normed scores<br />
ls<br />
data frame supplementary row coordinates<br />
as<br />
data frame inertia axis onto within axis<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Benzécri, J. P. (1983) Analyse de l’inertie intra-classe par l’analyse d’un tableau de correspondances.<br />
Les Cahiers de l’Analyse des données, 8, 351–358.<br />
Dolédec, S. and Chessel, D. (1987) Rythmes saisonniers et composantes stationnelles en milieu<br />
aquatique I- Description d’un plan d’observations complet par projection de variables. Acta Oecologica,<br />
Oecologia Generalis, 8, 3, 403–426.<br />
Examples<br />
data(meaudret)<br />
par(mfrow = c(2,2))<br />
pca1
withinpca 307<br />
withinpca<br />
Normed within Principal Component Analysis<br />
Description<br />
Usage<br />
performs a normed within Principal Component Analysis.<br />
withinpca(df, fac, scaling = c("partial", "total"),<br />
scannf = TRUE, nf = 2)<br />
Arguments<br />
df<br />
fac<br />
a data frame with quantitative variables<br />
a factor distributing the rows of df in classes<br />
scaling a string of characters as a scaling option :<br />
if "partial", for each factor level, the sub-array is centred and normed.<br />
If "total", for each factor level, the sub-array is centred and the total array is then<br />
normed.<br />
scannf<br />
nf<br />
Value<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
returns a list of the sub-class within of class dudi’. See within<br />
Author(s)<br />
Daniel Chessel<br />
Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉<br />
References<br />
Bouroche, J. M. (1975) Analyse des données ternaires: la double analyse en composantes principales.<br />
Thèse de 3ème cycle, Université de Paris VI.<br />
Examples<br />
data(meaudret)<br />
wit1
308 witwit.coa<br />
witwit.coa<br />
Internal Correspondence Analysis<br />
Description<br />
Usage<br />
witwit.coa performs an Internal Correspondence Analysis. witwitsepan gives the computation<br />
and the barplot of the eigenvalues for each separated analysis in an Internal Correspondence<br />
Analysis.<br />
witwit.coa(dudi, row.blocks, col.blocks, scannf = TRUE, nf = 2)<br />
## S3 method for class 'witwit':<br />
summary(object, ...)<br />
witwitsepan(ww, mfrow = NULL, csub = 2, plot = TRUE)<br />
Arguments<br />
dudi<br />
row.blocks<br />
col.blocks<br />
scannf<br />
nf<br />
object<br />
an object of class coa<br />
a numeric vector indicating the row numbers for each block of rows<br />
a numeric vector indicating the column numbers for each block of columns<br />
a logical value indicating whether the eigenvalues bar plot should be displayed<br />
if scannf FALSE, an integer indicating the number of kept axes<br />
an object of class witwit<br />
... further arguments passed to or from other methods<br />
ww<br />
Value<br />
mfrow<br />
csub<br />
plot<br />
an object of class witwit<br />
if FALSE, numeric results are returned<br />
returns a list of class witwit, coa and dudi (see as.dudi) containing<br />
rbvar<br />
lbw<br />
cvar<br />
cbw<br />
a data frame with the within variances of the rows of the factorial coordinates<br />
a data frame with the marginal weighting of the row classes<br />
a data frame with the within variances of the columns of the factorial coordinates<br />
a data frame with the marginal weighting of the column classes<br />
Author(s)<br />
Daniel Chessel Anne B Dufour 〈dufour@biomserv.univ-lyon1.fr〉 Correction by Campo Elías PARDO<br />
〈cepardot@cable.net.co〉
worksurv 309<br />
References<br />
Cazes, P., Chessel, D. and Dolédec, S. (1988) L’analyse des correspondances internes d’un tableau<br />
partitionné : son usage en hydrobiologie. Revue de Statistique Appliquée, 36, 39–54.<br />
Examples<br />
data(ardeche)<br />
coa1
310 yanomama<br />
<strong>Source</strong><br />
Rouanet, H. and Le Roux, B. (1993) Analyse des données multidimensionnelles. Dunod, Paris.<br />
References<br />
Le Roux, B. and Rouanet, H. (1997) Interpreting axes in multiple correspondence analysis: method<br />
of the contributions of points and deviation. Pages 197-220 in B. J. and M. Greenacre, editors.<br />
Visualization of categorical data, Acamedic Press, London.<br />
Examples<br />
data(worksurv)<br />
acm1
zealand 311<br />
Examples<br />
data(yanomama)<br />
gen
312 zealand<br />
s.label(cmdscale(d0), lab = as.character(1:13), neig = zealand$neig,<br />
sub = "Distance routiere", csub = 2)<br />
s.label(cmdscale(d1), lab = as.character(1:13), neig = zealand$neig,<br />
sub = "Distance routiere / Cailliez", csub = 2)<br />
s.label(cmdscale(d2), lab = as.character(1:13), neig = zealand$neig,<br />
sub = "Distance routiere / Lingoes", csub = 2)
Index<br />
∗Topic array<br />
cailliez, 36<br />
dist.binary, 58<br />
dist.dudi, 59<br />
dist.neig, 62<br />
dist.prop, 63<br />
dist.quant, 64<br />
dudi.pco, 86<br />
is.euclid, 113<br />
lingoes, 139<br />
mantel.randtest, 143<br />
mantel.rtest, 144<br />
pcoscaled, 192<br />
quasieuclid, 207<br />
∗Topic chron<br />
arrival, 17<br />
∗Topic datasets<br />
abouheif.eg, 5<br />
acacia, 6<br />
aminoacyl, 10<br />
apis108, 12<br />
ardeche, 13<br />
arrival, 17<br />
atlas, 19<br />
atya, 20<br />
avijons, 21<br />
avimedi, 23<br />
aviurba, 24<br />
bacteria, 25<br />
banque, 26<br />
baran95, 27<br />
bf88, 30<br />
bordeaux, 32<br />
bsetal97, 32<br />
buech, 34<br />
butterfly, 35<br />
capitales, 37<br />
carni19, 38<br />
carni70, 38<br />
carniherbi49, 39<br />
casitas, 40<br />
chatcat, 43<br />
chats, 44<br />
chazeb, 45<br />
chevaine, 45<br />
clementines, 46<br />
cnc2003, 47<br />
coleo, 51<br />
corvus, 53<br />
deug, 54<br />
doubs, 71<br />
dunedata, 88<br />
ecg, 89<br />
ecomor, 90<br />
elec88, 91<br />
escopage, 93<br />
euro123, 93<br />
fission, 94<br />
friday87, 97<br />
fruits, 97<br />
ggtortoises, 104<br />
granulo, 105<br />
hdpg, 107<br />
housetasks, 108<br />
humDNAm, 109<br />
ichtyo, 110<br />
irishdata, 112<br />
julliot, 114<br />
jv73, 116<br />
kcponds, 117<br />
lascaux, 138<br />
lizards, 140<br />
macaca, 141<br />
macon, 142<br />
mafragh, 142<br />
maples, 145<br />
mariages, 146<br />
meau, 149<br />
313
314 INDEX<br />
meaudret, 150<br />
microsatt, 152<br />
mjrochet, 154<br />
mollusc, 156<br />
monde84, 157<br />
morphosport, 158<br />
newick.eg, 168<br />
njplot, 173<br />
olympic, 174<br />
oribatid, 176<br />
ours, 185<br />
palm, 187<br />
pap, 188<br />
perthi02, 193<br />
presid2002, 199<br />
procella, 200<br />
rankrock, 215<br />
rhone, 217<br />
rpjdl, 220<br />
santacatalina, 247<br />
sarcelles, 248<br />
seconde, 265<br />
skulls, 267<br />
steppe, 269<br />
syndicats, 274<br />
t3012, 274<br />
tarentaise, 280<br />
taxo.eg, 282<br />
tintoodiel, 284<br />
tithonia, 285<br />
tortues, 286<br />
toxicity, 287<br />
trichometeo, 291<br />
ungulates, 292<br />
vegtf, 295<br />
veuvage, 296<br />
westafrica, 297<br />
worksurv, 303<br />
yanomama, 304<br />
zealand, 305<br />
∗Topic hplot<br />
add.scatter, 7<br />
area.plot, 14<br />
dotchart.phylog, 68<br />
dotcircle, 70<br />
kplot, 123<br />
kplot.foucart, 123<br />
kplot.mcoa, 124<br />
kplot.mfa, 125<br />
kplot.pta, 126<br />
kplot.sepan, 127<br />
kplot.statis, 129<br />
plot.phylog, 196<br />
s.arrow, 224<br />
s.chull, 225<br />
s.class, 227<br />
s.corcircle, 229<br />
s.distri, 230<br />
s.hist, 232<br />
s.image, 233<br />
s.kde2d, 235<br />
s.label, 236<br />
s.logo, 238<br />
s.match, 240<br />
s.multinom, 241<br />
s.traject, 243<br />
s.value, 245<br />
scatter, 250<br />
scatter.acm, 252<br />
scatter.coa, 252<br />
scatter.dudi, 253<br />
scatter.fca, 255<br />
sco.boxplot, 256<br />
sco.distri, 257<br />
sco.quant, 258<br />
score, 259<br />
score.acm, 260<br />
score.coa, 261<br />
score.mix, 263<br />
score.pca, 264<br />
symbols.phylog, 273<br />
table.cont, 275<br />
table.dist, 276<br />
table.paint, 277<br />
table.phylog, 278<br />
table.value, 279<br />
triangle.class, 288<br />
triangle.plot, 289<br />
∗Topic internal<br />
randtest-internal, 209<br />
∗Topic manip<br />
as.taxo, 18<br />
newick2phylog, 169<br />
phylog, 194<br />
PI2newick, 2<br />
∗Topic methods
INDEX 315<br />
krandtest, 130<br />
randtest, 210<br />
rtest, 221<br />
∗Topic models<br />
variance.phylog, 294<br />
∗Topic multivariate<br />
add.scatter, 7<br />
amova, 11<br />
between, 29<br />
cca, 41<br />
coinertia, 49<br />
disc, 55<br />
discrimin, 56<br />
discrimin.coa, 57<br />
dist.binary, 58<br />
dist.dudi, 59<br />
dist.genet, 60<br />
dist.neig, 62<br />
dist.prop, 63<br />
dist.quant, 64<br />
divc, 66<br />
divcmax, 67<br />
dpcoa, 72<br />
dudi, 74<br />
dudi.acm, 75<br />
dudi.coa, 77<br />
dudi.dec, 78<br />
dudi.fca, 79<br />
dudi.hillsmith, 81<br />
dudi.mix, 82<br />
dudi.nsc, 84<br />
dudi.pca, 85<br />
dudi.pco, 86<br />
EH, 1<br />
foucart, 95<br />
fuzzygenet, 99<br />
genet, 101<br />
inertia.dudi, 111<br />
kdist, 118<br />
kdist2ktab, 120<br />
kdisteuclid, 121<br />
kplot, 123<br />
kplot.foucart, 123<br />
kplot.mcoa, 124<br />
kplot.mfa, 125<br />
kplot.pta, 126<br />
kplot.sepan, 127<br />
kplot.statis, 129<br />
ktab, 131<br />
ktab.data.frame, 133<br />
ktab.list.df, 134<br />
ktab.list.dudi, 135<br />
ktab.match2ktabs, 136<br />
ktab.within, 137<br />
lingoes, 139<br />
mcoa, 147<br />
mfa, 151<br />
multispati, 160<br />
multispati.randtest, 163<br />
multispati.rtest, 164<br />
niche, 171<br />
optimEH, 175<br />
originality, 177<br />
orisaved, 179<br />
pcaiv, 189<br />
pcaivortho, 190<br />
procuste, 201<br />
procuste.randtest, 203<br />
procuste.rtest, 204<br />
pta, 205<br />
randEH, 208<br />
randtest.amova, 211<br />
randtest.between, 212<br />
randtest.coinertia, 213<br />
randtest.discrimin, 214<br />
reconst, 215<br />
rlq, 218<br />
rtest.between, 222<br />
rtest.discrimin, 223<br />
RV.rtest, 3<br />
RVdist.randtest, 4<br />
s.arrow, 224<br />
s.chull, 225<br />
s.class, 227<br />
s.corcircle, 229<br />
s.distri, 230<br />
s.hist, 232<br />
s.kde2d, 235<br />
s.label, 236<br />
s.logo, 238<br />
s.match, 240<br />
s.multinom, 241<br />
s.traject, 243<br />
s.value, 245<br />
scatter, 250<br />
scatter.acm, 252
316 INDEX<br />
scatter.coa, 252<br />
scatter.dudi, 253<br />
scatter.fca, 255<br />
sco.boxplot, 256<br />
sco.distri, 257<br />
sco.quant, 258<br />
score, 259<br />
score.acm, 260<br />
score.coa, 261<br />
score.mix, 263<br />
score.pca, 264<br />
sepan, 265<br />
statis, 268<br />
supcol, 270<br />
suprow, 271<br />
testdim, 283<br />
within, 299<br />
withinpca, 301<br />
witwit.coa, 302<br />
∗Topic nonparametric<br />
corkdist, 52<br />
mantel.randtest, 143<br />
mantel.rtest, 144<br />
multispati.randtest, 163<br />
multispati.rtest, 164<br />
procuste.randtest, 203<br />
procuste.rtest, 204<br />
randtest.amova, 211<br />
randtest.between, 212<br />
randtest.coinertia, 213<br />
randtest.discrimin, 214<br />
rtest.between, 222<br />
rtest.discrimin, 223<br />
RV.rtest, 3<br />
RVdist.randtest, 4<br />
∗Topic spatial<br />
gearymoran, 100<br />
gridrowcol, 106<br />
mld, 155<br />
multispati, 160<br />
multispati.randtest, 163<br />
multispati.rtest, 164<br />
orthobasis, 180<br />
orthogram, 183<br />
rlq, 218<br />
∗Topic ts<br />
gearymoran, 100<br />
mld, 155<br />
orthobasis, 180<br />
orthogram, 183<br />
∗Topic utilities<br />
<strong>ade4</strong>toR, 9<br />
bicenter.wt, 31<br />
kdisteuclid, 121<br />
mstree, 159<br />
neig, 165<br />
scalewt, 249<br />
uniquewt.df, 293<br />
[.kdist (kdist), 118<br />
[.ktab (ktab), 131<br />
abouheif.eg, 5<br />
acacia, 6<br />
acm.burt (dudi.acm), 75<br />
acm.disjonctif (dudi.acm), 75<br />
add.position.triangle<br />
(triangle.plot), 289<br />
add.scatter, 7, 251<br />
<strong>ade4</strong>toR, 9<br />
aminoacyl, 10<br />
amova, 11<br />
apis108, 12<br />
ardeche, 13<br />
area.plot, 14, 166<br />
area.util.class (area.plot), 14<br />
area.util.contour (area.plot), 14<br />
area.util.xy (area.plot), 14<br />
area2link (area.plot), 14<br />
area2poly (area.plot), 14<br />
arrival, 17<br />
as.data.frame.kdist (kdist), 118<br />
as.dudi, 302<br />
as.dudi (dudi), 74<br />
as.krandtest (krandtest), 130<br />
as.randtest (randtest), 210<br />
as.rtest (rtest), 221<br />
as.taxo, 18, 170<br />
atlas, 19<br />
atya, 20<br />
avijons, 21<br />
avimedi, 23<br />
aviurba, 24<br />
bacteria, 25<br />
banque, 26<br />
baran95, 27<br />
between, 29
INDEX 317<br />
bf88, 30<br />
bicenter.wt, 31<br />
bordeaux, 32<br />
boxplot.acm (dudi.acm), 75<br />
bsetal97, 32<br />
buech, 34<br />
butterfly, 35<br />
c.kdist (kdist), 118<br />
c.ktab (ktab), 131<br />
cailliez, 36<br />
capitales, 37<br />
carni19, 38<br />
carni70, 38<br />
carniherbi49, 39<br />
casitas, 40<br />
cca, 41, 42<br />
char2genet, 100<br />
char2genet (genet), 101<br />
chatcat, 43<br />
chats, 44<br />
chazeb, 45<br />
chevaine, 45<br />
circ.plot, 70<br />
clementines, 46<br />
cnc2003, 47<br />
coinertia, 49, 219<br />
col.names (ktab), 131<br />
col.names
318 INDEX<br />
is.ktab (ktab), 131<br />
julliot, 114<br />
jv73, 116<br />
kcponds, 117<br />
kdist, 118<br />
kdist2ktab, 120<br />
kdisteuclid, 121<br />
kplot, 123<br />
kplot.foucart, 123<br />
kplot.mcoa, 124<br />
kplot.mfa, 125<br />
kplot.pta, 126<br />
kplot.sepan, 127<br />
kplot.statis, 129<br />
krandtest, 130<br />
ktab, 131, 133–137<br />
ktab.data.frame, 132, 133<br />
ktab.list.df, 132, 134<br />
ktab.list.dudi, 132, 135<br />
ktab.match2ktabs, 132, 136<br />
ktab.util.addfactor
INDEX 319<br />
plot.procuste (procuste), 201<br />
plot.pta (pta), 205<br />
plot.randtest (randtest), 210<br />
plot.rlq (rlq), 218<br />
plot.rtest (rtest), 221<br />
plot.sepan (sepan), 265<br />
plot.statis (statis), 268<br />
plot.within (within), 299<br />
poly2area (area.plot), 14<br />
prep.fuzzy.var (dudi.fca), 79<br />
presid2002, 199<br />
print.amova (amova), 11<br />
print.between (between), 29<br />
print.coinertia (coinertia), 49<br />
print.corkdist (corkdist), 52<br />
print.discrimin (discrimin), 56<br />
print.dpcoa (dpcoa), 72<br />
print.dudi (dudi), 74<br />
print.foucart (foucart), 95<br />
print.kdist (kdist), 118<br />
print.krandtest (krandtest), 130<br />
print.ktab (ktab), 131<br />
print.mcoa (mcoa), 147<br />
print.mfa (mfa), 151<br />
print.multispati (multispati), 160<br />
print.neig (neig), 165<br />
print.niche (niche), 171<br />
print.orthobasis (orthobasis), 180<br />
print.pcaiv (pcaiv), 189<br />
print.phylog (phylog), 194<br />
print.procuste (procuste), 201<br />
print.pta (pta), 205<br />
print.randtest (randtest), 210<br />
print.rlq (rlq), 218<br />
print.rtest (rtest), 221<br />
print.sepan (sepan), 265<br />
print.statis (statis), 268<br />
print.within (within), 299<br />
procella, 200<br />
procuste, 201<br />
procuste.randtest, 203, 210<br />
procuste.rtest, 204, 222<br />
pta, 136, 205<br />
quasieuclid, 207<br />
radial.phylog (plot.phylog), 196<br />
randEH, 176, 208<br />
randtest, 131, 210, 222<br />
randtest-internal, 209<br />
randtest.amova, 12, 211<br />
randtest.between, 212<br />
randtest.coinertia, 213<br />
randtest.discrimin, 214<br />
randtest.rlq (rlq), 218<br />
rankrock, 215<br />
reciprocal.coa (score.coa), 261<br />
reconst, 215<br />
redo.dudi (dudi), 74<br />
rhone, 217<br />
rlq, 218<br />
row.names.ktab (ktab), 131<br />
row.names
320 INDEX<br />
scatterutil.eigen (scatter), 250<br />
scatterutil.ellipse (scatter), 250<br />
scatterutil.eti (scatter), 250<br />
scatterutil.grid (scatter), 250<br />
scatterutil.legend.bw.square<br />
(scatter), 250<br />
scatterutil.legend.square.grey<br />
(scatter), 250<br />
scatterutil.legendgris (scatter),<br />
250<br />
scatterutil.logo (s.logo), 238<br />
scatterutil.scaling (scatter), 250<br />
scatterutil.star (scatter), 250<br />
scatterutil.sub (scatter), 250<br />
sco.boxplot, 256, 260<br />
sco.distri, 257, 260<br />
sco.quant, 258, 260<br />
score, 259<br />
score.acm, 260<br />
score.coa, 261<br />
score.mix, 263<br />
score.pca, 264<br />
scores.neig (neig), 165<br />
scoreutil.base (score), 259<br />
seconde, 265<br />
sepan, 265<br />
skulls, 267<br />
statis, 268<br />
steppe, 269<br />
summary.coinertia (coinertia), 49<br />
summary.corkdist (corkdist), 52<br />
summary.dist (is.euclid), 113<br />
summary.mcoa (mcoa), 147<br />
summary.mfa (mfa), 151<br />
summary.multispati (multispati),<br />
160<br />
summary.neig (neig), 165<br />
summary.rlq (rlq), 218<br />
summary.sepan (sepan), 265<br />
summary.witwit (witwit.coa), 302<br />
supcol, 270<br />
suprow, 271<br />
symbols.phylog, 69, 273, 279<br />
syndicats, 274<br />
t.dudi (dudi), 74<br />
t.ktab (ktab), 131<br />
t3012, 274<br />
tab.names (ktab), 131<br />
tab.names
INDEX 321<br />
wavelet.filter, 181<br />
westafrica, 297<br />
within, 299, 301<br />
withinpca, 301<br />
witwit.coa, 302<br />
witwitsepan (witwit.coa), 302<br />
worksurv, 303<br />
yanomama, 304<br />
zealand, 305