Figure 2.

Predictor variable importance, as determined by CRF analysis. The cforest algorithm within Package party in R was applied to the ICEES multivariate dataset (see Figure 1 and Table 1) to determine the most important predictor variables in relation to the dependent variable of total annual ED or inpatient visits for respiratory issues. The vertical dashed line represents the significance threshold; values to the right of the line are significant. Variables are defined in Table 1.