Table 6 Wilcoxon signed-rank test: proposed ensemble versus individual classifiers on Statlog dataset
From: A hybrid cost-sensitive ensemble for heart disease prediction
| Â | RF | LR | SVM | ELM | KNN |
|---|---|---|---|---|---|
E | |||||
Z-value\(^{1}\) | − 2.805 | − 2.805 | − 2.670 | − 2.670 | − 2.803 |
p value | \(0.002^{**}\) | \(0.002^{**}\) | \(0.004^{**}\) | \(0.004^{**}\) | \(0.002^{**}\) |
Precision | |||||
Z-value | − 2.692 | − 2.829 | − 2.680 | − 2.677 | − 2.807 |
p value | \(0.004^{**}\) | \(0.002^{**}\) | \(0.004^{**}\) | \(0.004^{**}\) | \(0.002^{**}\) |
Recall | |||||
Z-value | − 2.374 | − 2.527 | − 2.388 | − 2.670 | − 2.536 |
p value | \(0.016^{*}\) | \(0.008^{**}\) | \(0.016^{*}\) | \(0.004^{**}\) | \(0.008^{**}\) |
G-mean | |||||
Z-value | − 2.803 | − 2.803 | − 2.666 | − 2.666 | − 2.803 |
p value | \(0.002^{**}\) | \(0.002^{**}\) | \(0.004^{**}\) | \(0.004^{**}\) | \(0.002^{**}\) |
MC | |||||
Z-value | − 2.654 | − 2.805 | − 2.670 | − 2.670 | − 2.803 |
p value | \(0.006^{**}\) | \(0.002^{**}\) | \(0.004^{**}\) | \(0.004^{**}\) | \(0.002^{**}\) |
Specificity | |||||
Z-value | − 1.825 | − 2.243 | − 2.371 | − 2.673 | − 2.675 |
p value | 0.086 | \(0.023^{*}\) | \(0.016^{*}\) | \(0.004^{**}\) | \(0.004^{**}\) |
AUC | |||||
Z-value | − 2.547 | − 2.599 | − 2.668 | − 2.666 | − 2.666 |
p value | \(0.008^{**}\) | \(0.006^{**}\) | \(0.004^{**}\) | \(0.004^{**}\) | \(0.004^{**}\) |