<p>A: Variables importance for the projection (VIP) of Hose pulling work capacity, using the training-set (n = 37). Green bars: Variables included in the final model. Blue bars: Variables were excluded from the model in Step 1, using VIP. Red bars: Variables were excluded from the model in Step 2 because the correlation was r ≥ 0.8 with another included variable. B: External validation is testing the selected model on the prediction-set.</p
<p>Selected normalization and variable influence on projection (VIP) cutoff values for model constru...
<p>Bivariate correlations (Pearson r) for simulated work tasks performance time (s): Carrying hose b...
(A) Importance ranking of the included variables. (B) Ten-fold cross-validation of the random forest...
<p>A: Variables importance for the projection (VIP) of Carrying hose baskets up stairs work capacity...
<p>A: Variables importance for the projection (VIP) of Carrying hose baskets over terrain work capac...
<p>A: Variables importance for the projection (VIP) of Demolition work capacity, using the training-...
<p>Selection of valid physical tests for prediction of Carrying hose baskets over terrain (n = 38) u...
<p>Selection of valid physical tests for prediction of firefighting physical work capacity (n = 36–3...
<p>For each species, the table shows the area under the curve (AUC) and regularized training gain (G...
<p>Training gain for each predictor variable alone (black) and the loss in training gain when the va...
<p><sup>a</sup> Predictors in the Model: (Constant), MOCA.</p><p><sup>b</sup> Predictors in the Mode...
<p>*Values are significantly different from random prediction (One-Sample t-test, p < 0.01, One-Samp...
Externally validated model discrimination for different predictor sets and modelling techniques: Val...
<p>Selected model coefficients, confidence interval and relative importance of the variables used.</...
<p>Results for feature selection, model selection and validation, using the two selection criteria a...
<p>Selected normalization and variable influence on projection (VIP) cutoff values for model constru...
<p>Bivariate correlations (Pearson r) for simulated work tasks performance time (s): Carrying hose b...
(A) Importance ranking of the included variables. (B) Ten-fold cross-validation of the random forest...
<p>A: Variables importance for the projection (VIP) of Carrying hose baskets up stairs work capacity...
<p>A: Variables importance for the projection (VIP) of Carrying hose baskets over terrain work capac...
<p>A: Variables importance for the projection (VIP) of Demolition work capacity, using the training-...
<p>Selection of valid physical tests for prediction of Carrying hose baskets over terrain (n = 38) u...
<p>Selection of valid physical tests for prediction of firefighting physical work capacity (n = 36–3...
<p>For each species, the table shows the area under the curve (AUC) and regularized training gain (G...
<p>Training gain for each predictor variable alone (black) and the loss in training gain when the va...
<p><sup>a</sup> Predictors in the Model: (Constant), MOCA.</p><p><sup>b</sup> Predictors in the Mode...
<p>*Values are significantly different from random prediction (One-Sample t-test, p < 0.01, One-Samp...
Externally validated model discrimination for different predictor sets and modelling techniques: Val...
<p>Selected model coefficients, confidence interval and relative importance of the variables used.</...
<p>Results for feature selection, model selection and validation, using the two selection criteria a...
<p>Selected normalization and variable influence on projection (VIP) cutoff values for model constru...
<p>Bivariate correlations (Pearson r) for simulated work tasks performance time (s): Carrying hose b...
(A) Importance ranking of the included variables. (B) Ten-fold cross-validation of the random forest...