<p>Higher values for the regularized training gain of the jack-knife test indicates greater contribution to the model for a variable (these values are not directly comparable between the different taxa). Test AUC numbers in parentheses are the standard deviation of the Test AUC scores. The top three variables are highlighted in bold for each taxon, both for the jack-knife variable contribution and test AUC values for Maxent models generated using a single variable. *indicates cross-validation cells that were eliminated due to low Test AUC scores.</p
<p>The graph shows the result of the Jackknife test of variable importance using regularized trainin...
<p>Each curve represents the regularized training gain of each variable used in isolation for each s...
<p>Summary of model performances (cross-validation AUC) for models with (A) topological variables ex...
<p>Higher values for the regularized training gain of the jack-knife test indicates greater contribu...
<p>*Values are significantly different from random prediction (One-Sample t-test, p < 0.01, One-Samp...
<p>Jacknife analysis for <i>Montipora</i>, <i>Leptoseris</i> and <i>Porites</i> showing the mean AUC...
<p>For each species, the table shows the area under the curve (AUC) and regularized training gain (G...
Statistical model validation tools such as cross-validation, jack-knifing model parameters and permu...
The first three rows achieved the highest AUC and the remaining rows achieved comparable AUC with a ...
<p>Symbols: TSS = True skill statistics, AUC = Area under the curve.</p><p>Model validation statisti...
<p>Jackknife tests (%) and the mean feature numbers of the SVM-based predictors for 30 samples.</p
Table S2. Results of jackknife test to test model reliability from <25 samples. Taxon, number of QDS...
<p>Variable values in bold indicate those chosen for final multi-layer models after taking the colli...
<p>The tradeoff between overfit and underfit for one of the five cross-validation data splits. Model...
<p>The figures show each variable’s contribution to (A) regularized training gain, and (B) test AUC ...
<p>The graph shows the result of the Jackknife test of variable importance using regularized trainin...
<p>Each curve represents the regularized training gain of each variable used in isolation for each s...
<p>Summary of model performances (cross-validation AUC) for models with (A) topological variables ex...
<p>Higher values for the regularized training gain of the jack-knife test indicates greater contribu...
<p>*Values are significantly different from random prediction (One-Sample t-test, p < 0.01, One-Samp...
<p>Jacknife analysis for <i>Montipora</i>, <i>Leptoseris</i> and <i>Porites</i> showing the mean AUC...
<p>For each species, the table shows the area under the curve (AUC) and regularized training gain (G...
Statistical model validation tools such as cross-validation, jack-knifing model parameters and permu...
The first three rows achieved the highest AUC and the remaining rows achieved comparable AUC with a ...
<p>Symbols: TSS = True skill statistics, AUC = Area under the curve.</p><p>Model validation statisti...
<p>Jackknife tests (%) and the mean feature numbers of the SVM-based predictors for 30 samples.</p
Table S2. Results of jackknife test to test model reliability from <25 samples. Taxon, number of QDS...
<p>Variable values in bold indicate those chosen for final multi-layer models after taking the colli...
<p>The tradeoff between overfit and underfit for one of the five cross-validation data splits. Model...
<p>The figures show each variable’s contribution to (A) regularized training gain, and (B) test AUC ...
<p>The graph shows the result of the Jackknife test of variable importance using regularized trainin...
<p>Each curve represents the regularized training gain of each variable used in isolation for each s...
<p>Summary of model performances (cross-validation AUC) for models with (A) topological variables ex...