I'm using the rfPermute to calculate the pval of the feature importance. Is it normal for a feature to be significant, but those with a higher %IncMSE to be not? Or have I done something wrong?

LFS.rfP2 <- rfPermute(
C40_WKS ~ ., 
data = LFS,
ntree = 1000,
na.action = na.omit, 
nrep = 500, 
num.cores = 6

  rp.importance(LFS.rfP2, scale = FALSE),
  alpha = 0.06

enter image description here


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.