[Biomod-commits] Two questions?

[Wilfried Thuiller]

Hi Alexandre,

> First, I am not sure how BIOMOD calculates the optimized ROC
> threshold. In the manual I found:"Optimized Threshold (...) It
> represents the best probability threshold
> maximizing the percentage of presence and absence correctly predicted
> for the evaluation data.". Does it mean maximizing the SUM of
> sensitivity and specificity?

It means minimizing the difference between sp and se (when the curves crossed). 

> Second, how can I calculate the final accuracy for a binary ensemble
> forecast model?

If the Ensemble Forecast has been carried out on the same points than the initial models, just type: Test=T in the Ensemble.Forecasting function:

Ensemble.Forecasting(Proj.name= "Future1", weight.method='Roc', PCA.median=TRUE, binary=TRUE, bin.method='Roc', Test=TRUE, repetition.models=TRUE)
Else you can use the inner function in BIOMOD or in R:

somers2(Fit, Obs) will give you the AUC. 

or to have the Kappa or TSS

KappaRepet(Obs, Fit, TSS = TRUE)

Hope it helps,
Wilfried



> 
> Thanks a lot for the help!
> 
> Alexandre
> _______________________________________________
> 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 63 54 53
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/20100222/7e699eec/attachment.html