Bias in random forest variable importance measures: Illustrations, sources and a solution

BMC Bioinformatics

Table 3 Rates of correct identifications of the informative variable for the power case

Rates of correct identifications of the informative variable with the scaled and unscaled permutation importance of the randomForest method, applied with sampling with and without replacement, as compared to those of the cforest method, applied with sampling with and without replacement, as a function of the degree of dependence (indicated by the relevance parameter, cf. Table 2) between the informative variable X₂ and the response. (Standard errors of the rates of correct identifications r over 1000 iterations can easily be computet by se = $\sqrt{r \cdot (1 - r) / 1000}$ .)

ISSN: 1471-2105