See varimp.cforest.
# S3 method for pmforest
varimp(object, nperm = 1L, OOB = TRUE,
risk = function(x, ...) -objfun(x, sum = TRUE, ...),
conditional = FALSE, threshold = 0.2, ...)DESCRIPTION.
the number of permutations performed.
a logical determining whether the importance is computed from the out-of-bag sample or the learning sample (not suggested).
the risk to be evaluated. By default the objective function (e.g. log-Likelihood) is used.
a logical determining whether unconditional or conditional computation of the importance is performed.
the value of the test statistic or 1 - p-value of the association between the variable of interest and a covariate that must be exceeded inorder to include the covariate in the conditioning scheme for the variable of interest (only relevant if conditional = TRUE).
passed on to objfun.
A vector of 'mean decrease in accuracy' importance scores.