[Biomod-commits] ANN and VarImportance

[Wilfried Thuiller]

yes but this probably the way it is for this algorithm. 
The method to estimate variable importance is the same for all algorithms

I gather that host presence-absence is also correlated to other variables, right? 


Le 15 nov. 2010 à 20:28, Cris Cris a écrit :

> When I include the presence-absence of a host specie as a variable, the VarImportance of ANN shows only zeros associated with the host layer.
> All other algorithms show the opposite: the host is the most important variable.
> All the rest is ok: I can plot the ANN's results and reach some good values of AUC but this result of VarImportance seems strange.
> Thank you for the support.
> _______________________________________________
> Biomod-commits mailing list
> Biomod-commits at lists.r-forge.r-project.org
> https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits

--------------------------
Dr. Wilfried Thuiller
Laboratoire d'Ecologie Alpine, UMR CNRS 5553
Université Joseph Fourier
BP53, 38041 Grenoble cedex 9, France
tel: +33 (0)4 76 51 44 97
fax: +33 (0)4 76 51 42 79

Email: wilfried.thuiller at ujf-grenoble.fr
Home page: http://www.will.chez-alice.fr
Website: http://www-leca.ujf-grenoble.fr/equipes/tde.htm

FP6 European MACIS project: http://www.macis-project.net
FP6 European EcoChange project: http://www.ecochange-project.eu





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/biomod-commits/attachments/20101115/bf874f14/attachment-0001.htm>