Skip to main content

Table 3 Random forest spatial model results.

From: Local impact of temperature and precipitation on West Nile virus infection in Culex species mosquitoes in northeast Illinois, USA

Variables Tested and Model Type Year R2 Most important variables in model
All variables Random Forest All   Precip W33, W19, W28
    Temp W27
   76.89 Pct Black
  2004 81.77 Precip W23, W29, W33
  2005   Precip W28, W21
   64.48 Temp W33
  2006 74.76 Precip W29, W18, W19, W33
  2007   Precip W15, W28
   62.88 Temp W17
Weather variables only Random Forest All   Precip W33, W19
   78.77 Temp W27
  2004 82.99 Precip W33, W23, W29
  2005 70.55 Precip W32, W28, W19
  2006 77.03 Precip W33, W29, W19
  2007   Precip W15, W21
   67.01 Temp W17
Non-weather variables only. Random Forest All 13.27 Pct Black, Human population, Elevation range
  2004 47.34 Pct Black, Maximum elevation, Minimum elevation
  2005 34.47 % pre-40's housing, Pct Black, % 50's housing
  2006 42.27 Pct Black, maximum elevation, % 90's housing
  2007 37.95 Pct Black, maximum elevation, mean elevation
  1. The R2 value indicates the ability of random forests to predict mosquito infection in weeks 32 to 34. Also included are the most important variables from the models listed in order of importance. Results are divided according to which variables were included in the models. See Additional File 3: Spatial, for a regression tree graphic.