Skip to main content

Table 4 Regression tree 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 Regression Tree All   Precip W17, W19
   48.24 Temp W35
  2004   Precip W29, W28
   70.95 Temp W28
  2005   Temp W33
   55.57 Precip W24, W26
  2006 67.22 Temp W35, W27
    Precip W19
  2007   Temp W17, W22
   61.63 Mean elevation
Weather variables only Regression Tree All   Precip W17, W19
   48.24 Temp W35
  2004   Precip W28, W29
   68.67 Temp W28
  2005   Temp W33
   56.27 Precip W24, W26
  2006   Temp W35, W27
   67.99 Precip W19
  2007   Temp W17, W22
   61.16 Precip W15
Non-weather variables only Regression Tree All 8.28 Impervious surface, % pre-40's housing, % 50's housing
  2004 47.41 Minimum elevation, Mean elevation, impervious surface
  2005 32.23 Maximum elevation, impervious surface, Human population
  2006 48.83 Maximum elevation, impervious surface, Human population
  2007 42.03 Maximum elevation, impervious surface, Human population
  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.