[Biomod-commits] "fitted probabilities numerically 0 or 1 occurred" and "algorithm did not converge"

[Wilfried Thuiller]

Hi there,

These are not errors but warnings concerning the GLM function (or sometimes GAM)  usually which did not really converge appropriately. 
Note that you still get the results anyway.

I guess your species or whatever dependent variable has a very low or very high prevalence and that the algorithm have problem to have a good fit. Note that this is not a BIOMOD problem but really a data-algorithm problem. In any case, check the results, they might not be that bad after all. 

Best
Wilfried




Le 27 oct. 2011 à 21:40, Frederico Mestre a écrit :

> Hello:
>  
> I’m running my models and I keep getting these errors: “fitted probabilities numerically 0 or 1 occurred” and “algorithm did not converge”.
>  
> I understand that this means that one of the predictor variables is separating perfectly the values of the dependent variable. My variables are not supposed to be so highly related to the  dependent variable. The dependent variable is not derived from the predictors.
>  
> I tried than to use other variables (which I know are not very good predictors) and I got the same errors.
>  
> Is it possible that this is somehow related with some error in BIOMOD or with the structure of my data?
>  
> Thanks,
>  
> Frederico Mestre
>  
> _______________________________________________
> 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
Personal website: http://www.will.chez-alice.fr
Team website: http://www-leca.ujf-grenoble.fr/equipes/emabio.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/20111027/81506aa6/attachment.htm>