Table 5.
The performance of models.
| NFA total | NFA approach | NFA avoidance | ||||
|---|---|---|---|---|---|---|
| r | R 2 | r | R 2 | r | R 2 | |
| XGB | 0.34** | 0.11 | 0.31** | 0.09 | 0.25* | 0.04 |
| LR | 0.26* | 0.04 | 0.21 | 0.02 | 0.2 | 0.03 |
| SVR | 0.09 | 0.001 | 0.12 | 0.009 | 0.08 | 0.002 |
| LASSO | 0.18 | 0.03 | 0.16 | 0.02 | 0.12 | 0.01 |
| Ridge | 0.17 | 0.02 | 0.13 | 0.01 | 0.12 | 0.01 |
| ETR | 0.27** | 0.07 | 0.26* | 0.06 | 0.22 | 0.05 |
| RF | 0.26* | 0.06 | 0.26* | 0.06 | 0.18 | 0.03 |
| GBR | 0.27** | 0.06 | 0.27** | 0.06 | 0.23 | 0.04 |
“r” is the Pearson correlation coefficient between predictive scores and NFA questionnaire scores (*p < 0.05, **p < 0.01); R2 is the proportion of the variability in the response variable; XGB, Extreme Gradient Boosting; LR, Linear Regression; SVR, Support Vector Regression; GBR, Gradient Boosting Regression; RF, Random Forest Regression; LASSO, Least absolute shrinkage and selection operator; Ridge, Ridge Regression; ETR, Extra Trees Regression.