Skip to main content


Figure 2 | Malaria Journal

Figure 2

From: Local topographic wetness indices predict household malaria risk better than land-use and land-cover in the western Kenya highlands

Figure 2

Change in mean-squared-error resulting from the addition of land-cover/land-use variables to the best-fitting topographic predictive model for each random subset of houses. The results of 300 split-sample repetitions are pictured (the box represents the 25th to 75th percentile, while whiskers show range). Negative values indicate that addition of the variable improved the accuracy of the model in predicting malaria risk.

Back to article page