Skip to main content

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

From: Mapping hotspots of malaria transmission from pre-existing hydrology, geology and geomorphology data in the pre-elimination context of Zanzibar, United Republic of Tanzania

Wet season Number of trees fitted = 1600
  AUC Std. Error
Calibration 0.9  
Cross-validation 0.89 0.05
Dry season Number of trees fitted = 1350
  AUC Std. Error
Calibration 0.86  
Cross-validation 0.8 0.075