<meta http-equiv="CONTENT-TYPE" content="text/html; charset=utf-8"><title></title><meta name="GENERATOR" content="OpenOffice.org 3.2 (Win32)"><style type="text/css">
<!--
@page { margin: 2cm }
P { margin-bottom: 0.21cm }
-->
</style>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><font size="2">Hello fellow Biomodders,</font></p><p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><font size="2"><br>After using Biomod for a while, I'm
still confused by the Evaluation.results file, so here is my own
interpretation which I don't know if it's correct. I hope I don't
confuse anyone more now...
</font></p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><font size="2">Say I'm running models with no
pseudoabsences, one repetition run and 80-20 split.
Evaluation.results.kappa is a list of data frames $Sp1_full and
$Sp1_full_rep1.
</font></p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><font size="2">For repetition 1, the first column is
the crossvalidation, from comparing predictions on the 20% evaluation
data (from the models calibrated on 80% of data) to original
distribution data. But how are the 'leftover' columns made?
Crossvalidation with the 80%-models applied on 100% of data? Are
Cutoffs made by comparing the predictions from 80%-models on 20%
evaluation data, to the real distribution (in the same 20% of
locations)?</font></p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><font size="2">For
$Sp1_full, the first column is the average of all cross-validations
(so it's the same value in my case). Are the other columns the model
calibrated on 100% of the data, i.e. a 'final model'? Are those
Cutoffs made by the 100%-models applied on the entire studyarea?
Values for Sensitivity and Specificity seem to be generally higher
than for the repetitions. (The manual says 'using the model built
with all data for calibration' which confuses me). </font>
</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><font size="2">Finally, does Biomod make a 'final
model' trained on 100% of the data?</font></p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><font size="2">Thank you very much,
</font></p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><font size="2">Hedvig Nenzén</font></p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><br>
</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">One of my species as an example:
</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">> Evaluation.results.Kappa
</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">$Sp1_full</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"> Cross.validation indepdt.data
total.score Cutoff Sensitivity Specificity</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">ANN 0.688 none
0.7149572 495.00 89.70370 81.40044</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">CTA 0.735 none
0.8010009 435.16 94.88889 84.13567</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">GAM 0.683 none
0.7108026 526.29 90.59259 79.75930</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">GBM 0.738 none
0.7730225 588.36 93.85185 82.38512</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">GLM 0.670 none
0.6884088 588.82 87.18519 81.72867</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">MARS 0.759 none
0.7729465 454.08 93.03704 83.47921</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">FDA 0.733 none
0.7568880 372.35 92.66667 82.16630</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">RF 0.745 none
1.0000000 440.00 100.00000 100.00000</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">SRE 0.545 none
0.5607607 10.00 91.18519 62.69147</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><br>
</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">$Sp1_full_rep1</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"> Cross.validation indepdt.data
total.score Cutoff Sensitivity Specificity</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">ANN 0.688 none
0.7166007 486.71 89.92593 81.29103</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">CTA 0.735 none
0.8030243 407.90 93.77778 85.88621</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">GAM 0.683 none
0.7103411 546.15 90.22222 80.19694</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">GBM 0.738 none
0.7740735 572.40 94.66667 81.40044</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">GLM 0.670 none
0.6887384 589.41 86.96296 82.05689</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">MARS 0.759 none
0.7715822 502.25 92.51852 84.02626</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">FDA 0.733 none
0.7554794 355.14 93.03704 81.50985</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">RF 0.745 none
0.9494617 480.00 98.29630 96.49891</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;">SRE 0.545 none
0.5783646 10.00 90.66667 65.20788</p>
<p style="margin-bottom: 0cm; font-family: arial,helvetica,sans-serif;"><br>
</p>
<p style="margin-bottom: 0cm;"><br>
</p>
<p style="margin-bottom: 0cm;" align="LEFT"><br>
</p>
<p style="margin-bottom: 0cm;"><br>
</p>