Skip to main content
. 2016 Oct 12;6(22):7976–7990. doi: 10.1002/ece3.2507

Table 1.

Climate variables from the PRISM Climate Group (2013) used in Random Forests models for both current and historical classifications. Number represents variable importance in each model as assessed using the Gini impurity index, which ranks variables based on the decrease of the accuracy of an RF model when a variable is excluded, such that important variables lead to a large decrease in model performance when excluded (Breiman, 2001; Liaw & Wiener, 2002). Dashes mean a variable was not included in the final model

Historical Current
Red‐breasted Red‐naped Red‐breasted Red‐naped
Maximum precipitation 1 4 5
Minimum precipitation 4
Mean annual precipitation 5 3 4
Precipitation seasonality 2 1 1
Mean temperature 6 2 7 7
Maximum temperature of warmest month
Mean maximum temperature 4 5 5 3
Mean minimum temperature 7 1 6 6
Minimum temperature of coldest month 3 3 2 2