[Biomod-commits] threshold criteria

Wilfried Thuiller wilfried.thuiller at ujf-grenoble.fr
Fri Sep 2 14:00:59 CEST 2011


Dear Jesus,


> Hello, I would like to know if the threshold criteria used to convert to a binary prediction is the Maximum sensitivity + specificity or which one does BIOMOD uses?

Depends on which method

For TSS and Kappa, this is the threshold maximizing the TSS or Kappa. We used an increment of 0.01 and test all possible value and select the one maximizing the statistic.
For AUC, this is the threshold minimizing the difference between se and sp. 

> I was also wondering if you are analysing the Evaluation results output by TSS, then in the final model the TSS value is on the Spp.full.total.Score column is that right?

Depends in you have repetition or not. If you have repetition you first have the full model outputs which does have the TSS value for the final (100% of data) model. 

If you want to compare the different techniques, better to compare the Cross-validation outputs however.

Wilfried



> 
> Thank you in advance,
> 
> Jesus
> _______________________________________________
> 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/20110902/0317a11a/attachment.htm>


More information about the Biomod-commits mailing list