<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div>Hi Pep,</div><div>of course this is possible to have a better value with an ensemble forecasting than with the best model. This is even why we use ensemble forecasting!</div><div><br></div><div>The advantage is that each model bring its own information and that all the information put together is more informative than the one coming from the best single model.</div><div><br></div><div>Hope I am clear. </div><div><br></div><div>Wilfried</div><div><br></div><div><br></div><br><div><div>Le 4 nov. 09 à 17:02, Pep Serra a écrit :</div><br class="Apple-interchange-newline"><blockquote type="cite"> <div bgcolor="#ffffff" text="#000000"> Sorry, I meant Evaluation.results.TSS when I wrote Evaluation.results.Kappa<br> <br> <br> <br> <br> En/na Pep Serra ha escrit: <blockquote cite="mid:4AF1A127.3090402@uab.cat" type="cite">Hi BIOMODers,<br> <br> I run BIOMOD for some species and I obtained these results which are a bit difficult to interpret to me:<br> <br> I am checking AUC and TSS model by model and comparing it to the Ensemble modeling approach:<br> <br> <br> <table style="border-collapse: collapse; width: 120pt;" border="0" cellpadding="0" cellspacing="0" width="160"> <col style="width: 60pt;" span="2" width="80"> <tbody> <tr style="height: 15pt;" height="20"> <td style="height: 15pt; width: 60pt;" height="20" width="80"><br> </td> <td style="width: 60pt;" width="80">TSS</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20"><br> </td> <td>mean</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">ANN</td> <td align="right">0.70566667</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">CTA</td> <td align="right">0.7495</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">GAM</td> <td align="right">0.75466667</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">GBM</td> <td align="right">0.77866667</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">GLM</td> <td align="right">0.7365</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">MARS</td> <td align="right">0.75016667</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">MDA</td> <td align="right">0.69866667</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">RF</td> <td align="right">0.80516667</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">SRE</td> <td align="right">0.436</td> </tr> <tr style="height: 15pt;" height="20"> <td style="height: 15pt;" height="20">EF</td> <td align="right">0.97055927</td> </tr> </tbody> </table> <br> 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.<br> 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)?<br> <br> Thanx !<br> <pre wrap="">_______________________________________________
Biomod-commits mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Biomod-commits@lists.r-forge.r-project.org">Biomod-commits@lists.r-forge.r-project.org</a>
<a class="moz-txt-link-freetext" href="https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits">https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits</a>
</pre> </blockquote> <br> </div> <span><josep_serra.vcf></span>_______________________________________________<br>Biomod-commits mailing list<br><a href="mailto:Biomod-commits@lists.r-forge.r-project.org">Biomod-commits@lists.r-forge.r-project.org</a><br>https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/biomod-commits<br></blockquote></div><br><div> <span class="Apple-style-span" style="border-collapse: separate; color: rgb(0, 0, 0); font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: 2; text-align: auto; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-border-horizontal-spacing: 0px; -webkit-border-vertical-spacing: 0px; -webkit-text-decorations-in-effect: none; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0; "><div style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; "><div>-------------------------</div><div>Dr. Wilfried Thuiller</div><div>Laboratoire d'Ecologie Alpine, UMR CNRS 5553</div><div>Université Joseph Fourier</div><div>BP53, 38041 Grenoble cedex 9, France</div><div>tel: +33 (0)4 76 63 54 53</div><div>fax: +33 (0)4 76 51 42 79</div><div><br></div><div>Email: <a href="mailto:wilfried.thuiller@ujf-grenoble.fr">wilfried.thuiller@ujf-grenoble.fr</a><br>Home page: <a href="http://www.will.chez-alice.fr/">http://www.will.chez-alice.fr</a><br>Website: <a href="http://www-leca.ujf-grenoble.fr/equipes/tde.htm">http://www-leca.ujf-grenoble.fr/equipes/tde.htm</a><br><br>FP6 European MACIS project: <a href="http://www.macis-project.net/">http://www.macis-project.net</a><br>FP6 European EcoChange project: <a href="http://www.ecochange-project.eu/">http://www.ecochange-project.eu</a></div><div><br></div><div><br></div><div><br></div></div></span><br class="Apple-interchange-newline"> </div><br></body></html>