[Biomod-commits] evaluating results

Pep Serra josep.serra at uab.cat
Wed Nov 4 16:43:35 CET 2009


I run BIOMOD for some species and I obtained these results which are a 
bit difficult to interpret to me:

I am checking AUC and TSS model by model and comparing it to the 
Ensemble modeling approach:


ANN 	0.70566667
CTA 	0.7495
GAM 	0.75466667
GBM 	0.77866667
GLM 	0.7365
MARS 	0.75016667
MDA 	0.69866667
RF 	0.80516667
SRE 	0.436
EF 	0.97055927

I am producing an ensemble forecasting giving weights according to the 
TSS statistic (decay=1.6). For each model I used the cross-validation 
result out of Evaluation.results.Kappa.
Is it possible to obtain a TSS statistic even much better than the best 
model and the best run of the best model (according to TSS)?

Thanx !
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.r-forge.r-project.org/pipermail/biomod-commits/attachments/20091104/3269d53d/attachment.htm 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: josep_serra.vcf
Type: text/x-vcard
Size: 448 bytes
Desc: not available
Url : http://lists.r-forge.r-project.org/pipermail/biomod-commits/attachments/20091104/3269d53d/attachment.vcf 

More information about the Biomod-commits mailing list