Table 3 Boosted Regression Tree modelling results for predicting hotspots of malaria infection for the 2011 dry and wet seasons using variables describing the physical geography of Unguja, Zanzibar
Wet season | Number of trees fitted = 1600 | |
|---|---|---|
| Â | AUC | Std. Error |
Calibration | 0.9 | Â |
Cross-validation | 0.89 | 0.05 |
Dry season | Number of trees fitted = 1350 | |
| Â | AUC | Std. Error |
Calibration | 0.86 | Â |
Cross-validation | 0.8 | 0.075 |