<html><head></head><body><div style="font-family: Verdana;font-size: 12.0px;"><div>Dear Mathieu,<br/></div><div><br/></div><div>thank you for your quick response and the clarification. Sorry I did not fill in a subject. I have actually never been active in a mailing list before.<br/></div><div><br/></div><div>You are saying that the eigenvalues are the specialization values and that the specialization accounted for by the marginality can also be calculated as described by your script. Can´t I then use the value of the specialization accounted for by the marginality axis to sum it up with the eigenvalues of the specialization axes to calculate a proportion of specialization explained by the marginality axis and by each specialization axis?<br/></div><div><br/></div><div>For example: <br/></div><div><br/></div><div>ev_mar<-sum(enfa1$pr)/length(enfa1$pr) * sum(enfa1$li$Mar^2)/sum((niche1$Mar -<br/>mean(niche1$Mar))^2)<br/></div><div><br/></div><div>and then to calculate the proportion for the example of the first eigenvalue of 1.565:<br/></div><div><br/></div><div>1.565/sum(enfa1$s+ev_mar)<br/></div><div>[1] 0.2045417<br/></div><div><br/></div><div>Greetings<br/></div><div>Lisa<br/>
<br/></div><div name="quote" style="margin: 10px 5px 5px 10px; padding: 10px 0pt 10px 10px; border-left: 2px solid rgb(195, 217, 229); word-wrap: break-word;">
<div style="margin: 0pt 0pt 10px;">
<b>Gesendet:</b> Donnerstag, 01. März 2012 um 16:18 Uhr<br/>
<b>Von:</b> "Mathieu Basille" <basille@ase-research.org><br/>
<b>An:</b> r-sig-geo@r-project.org<br/>
<b>Betreff:</b> Re: [R-sig-Geo] Meaning of specialization eigenvalues in ENFA
<br/></div>
<div name="quoted-content">
Dear Lisa,<br/>
<br/>
Please use a sensible subject in the future (I corrected it for better <br/>
archiving and to help you get more answers).<br/>
<br/>
The specialization can not be interpreted in terms of explained variance. <br/>
The specialization on any axis is the ratio of the available variance over <br/>
the used variance, which do not sum up to 1 on every axis. The <br/>
specialization values are given by the eigenvalues of an enfa object. Let's <br/>
take the example in ?enfa:<br/>
<br/>
library(adehabitatHS)<br/>
<br/>
data(lynxjura)<br/>
map <- lynxjura$map<br/>
locs <- lynxjura$locs<br/>
locs <- locs[slot(locs, "data")[,2]!="D",]<br/>
slot(map,"data")[,4] <- sqrt(slot(map,"data")[,4])<br/>
tab <- slot(map, "data")<br/>
pr <- slot(count.points(locs, map), "data")[,1]<br/>
pc <- dudi.pca(tab, scannf = FALSE)<br/>
(enfa1 <- enfa(pc, pr, scannf = FALSE, nf = 3))<br/>
<br/>
Here, the variance available on the first axis of specialization is 1.57 <br/>
times higher than the variance used on this axis. We can actually compute <br/>
these values using the ratio of variances:<br/>
<br/>
niche1 <- enfa1$li[rep(1:length(enfa1$pr), enfa1$pr), ]<br/>
sum(enfa1$pr)/length(enfa1$pr) * sum(enfa1$li$Spe1^2)/sum(niche1$Spe1^2)<br/>
sum(enfa1$pr)/length(enfa1$pr) * sum(enfa1$li$Spe2^2)/sum(niche1$Spe2^2)<br/>
enfa1$s<br/>
<br/>
Note, however, that the marginality axis also accounts for some <br/>
marginality. To compute the specialization on the marginality axis, it is <br/>
exactly the same approach:<br/>
<br/>
sum(enfa1$pr)/length(enfa1$pr) * sum(enfa1$li$Mar^2)/sum((niche1$Mar - <br/>
mean(niche1$Mar))^2)<br/>
<br/>
Hope this helps,<br/>
Mathieu.<br/>
<br/>
<br/>
Le 01/03/2012 05:42, Lisa Freudenberger a écrit :<br/>
> Dear all,<br/>
><br/>
> I hope this is the right place to post my question and that someone might<br/>
> be able to help me. I am performing an ENFA with species data and<br/>
> environmental variables unsing the adehabitat package. What I know how to<br/>
> get are the eigenvalues of the specialization axes and the coefficients for<br/>
> all environmental variables.<br/>
><br/>
> However I was wondering how you can calculate the percentage of variance<br/>
> (specialization) explained by each axis from these data. As I know the<br/>
> marginality axis always explains the whole marginality as well as part of<br/>
> the specialization. My initial thought was to sum up all eigenvalues and<br/>
> calculate the proportional values for each eigenvalue, meaning<br/>
> eigenvalue/sum of eigenvalues. But as I do not get an eigenvalue for the<br/>
> marginality axis I can´t build the sum of all of them.<br/>
><br/>
> Does anyone of you have an idea how to solve this problem?<br/>
><br/>
> Any help is appreciated!<br/>
><br/>
> All the best<br/>
> Lisa<br/>
><br/>
><br/>
> Ihr WEB.DE Postfach immer dabei: die kostenlose WEB.DE Mail App für iPhone<br/>
> und Android.<br/>
> *<a href="https://produkte.web.de/freemail_mobile_startseite/*" target="_blank">https://produkte.web.de/freemail_mobile_startseite/*</a><br/>
><br/>
><br/>
><br/>
> _______________________________________________<br/>
> R-sig-Geo mailing list<br/>
> R-sig-Geo@r-project.org<br/>
> <a href="https://stat.ethz.ch/mailman/listinfo/r-sig-geo" target="_blank">https://stat.ethz.ch/mailman/listinfo/r-sig-geo</a><br/>
<br/>
-- <br/>
<br/>
~$ whoami<br/>
Mathieu Basille, Post-Doc<br/>
<br/>
~$ locate<br/>
Laboratoire d'Écologie Comportementale et de Conservation de la Faune<br/>
+ Centre d'Étude de la Forêt<br/>
Département de Biologie<br/>
Université Laval, Québec<br/>
<br/>
~$ info<br/>
<a href="http://ase-research.org/basille" target="_blank">http://ase-research.org/basille</a><br/>
<br/>
~$ fortune<br/>
``If you can't win by reason, go for volume.''<br/>
Calvin, by Bill Watterson.<br/>
<br/>
_______________________________________________<br/>
R-sig-Geo mailing list<br/>
R-sig-Geo@r-project.org<br/>
<a href="https://stat.ethz.ch/mailman/listinfo/r-sig-geo" target="_blank">https://stat.ethz.ch/mailman/listinfo/r-sig-geo</a><br/>
</div>
</div></div> <br><br><table cellpadding="0" cellspacing="0" border="0"><tr><td style="font-family:verdana; font-size:12px; line-height:17px;border-top:1px solid #000000">Ihr WEB.DE Postfach immer dabei: die kostenlose WEB.DE Mail App für iPhone und Android. <br><a href="https://produkte.web.de/freemail_mobile_startseite/"><b>https://produkte.web.de/freemail_mobile_startseite/</b></a></td></tr></table>
</body></html>