Table 14 Wilcoxon signed-rank test: proposed ensemble versus individual classifiers on Hungarian dataset
From: A hybrid cost-sensitive ensemble for heart disease prediction
| Â | RF | LR | SVM | ELM | KNN |
|---|---|---|---|---|---|
E | |||||
Z-value\(^{1}\) | − 2.312 | − 2.244 | − 2.668 | − 2.821 | − 2.803 |
p value\(^{2}\) | \(0.020^{*}\) | \(0.022^{*}\) | \(0.004^{**}\) | \(0.002^{**}\) | \(0.002^{**}\) |
Precision | |||||
Z-value | − 2.446 | − 2.271 | − 2.689 | − 2.840 | − 2.814 |
p value | \(0.016^{*}\) | \(0.023^{*}\) | \(0.004^{**}\) | \(0.002^{**}\) | \(0.002^{**}\) |
Recall | |||||
Z-value | − 2.075 | − 2.100 | − 2.670 | − 2.814 | − 2.310 |
p value | \(0.035^{*}\) | \(0.039^{*}\) | \(0.004^{**}\) | \(0.002^{**}\) | \(0.020^{*}\) |
G-mean | |||||
Z-value | − 2.429 | − 2.293 | − 2.668 | − 2.805 | − 2.803 |
p value | \(0.012^{*}\) | \(0.020^{*}\) | \(0.004^{**}\) | \(0.002^{**}\) | \(0.002^{**}\) |
MC | |||||
Z-value | − 1.956 | − 2.041 | − 2.668 | − 2.821 | − 2.803 |
p value | 0.051 | \(0.043^{*}\) | \(0.004^{**}\) | \(0.002^{**}\) | \(0.002^{**}\) |
Specificity | |||||
Z-value | − 1.955 | − 1.960 | − 1.365 | − 2.668 | − 2.803 |
p value | 0.055 | 0.055 | 0.195 | \(0.004^{**}\) | \(0.002^{**}\) |
AUC | |||||
Z-value | − 2.803 | − 2.346 | − 2.803 | − 2.803 | − 2.805 |
p value | \(0.002^{**}\) | \(0.016^{*}\) | \(0.002^{**}\) | \(0.002^{**}\) | \(0.002^{**}\) |