<font><font face="tahoma,sans-serif">Hello modelers,</font></font><div><font face="tahoma, sans-serif"><br></font></div><div><font face="tahoma, sans-serif">I have my DataSplit set at 100 and have a separate test file. This gives me no cross.validation score but it gives me independent data score (indepdt.data in Evaluaiton.results.Roc). I set weight.method='Roc' for the function Ensemble.Forecasting. </font><span style="font-family:tahoma,sans-serif">How the software computes ensemble probabilities is not clear in the manual.</span><span style="font-family:tahoma,sans-serif"> </span><span style="font-family:tahoma,sans-serif">But somewhere I came across the information that the weights are based on cross validated evaluation score. Since I do not have such score, the function should not work. Instead, it gives me weight:</span></div>
<div><span style="font-family:tahoma,sans-serif"><div><br></div><div>$weights</div><div> ANN CTA GAM GBM GLM MARS FDA RF SRE</div><div>PA1 0 0 0.1729 0.2766 0.108 0 0 0.4425 0</div><div><br></div>
</span></div><div><span style="font-family:tahoma,sans-serif">Where are these weights coming from? These numbers do not match with any column in Evaluation.results (after rescaling to make the total =1). </span></div><div>
<a href="https://r-forge.r-project.org/scm/viewvc.php/pkg/R/Ensemble.Forecasting.R?view=markup&root=biomod&pathrev=168">https://r-forge.r-project.org/scm/viewvc.php/pkg/R/Ensemble.Forecasting.R?view=markup&root=biomod&pathrev=168</a> </div>
<div><div><div><br></div><div>Thanks in advance,</div><div>Kumar</div>-- <br><font color="#666666" face="tahoma, sans-serif">Section of Integrative Biology<br>University of Texas at Austin<br>Austin, Texas 78712, USA</font><br>
</div></div>