Displaying 1 result from an estimated 1 matches for "comm_heir".
2010 Mar 16
1
Regarding variable importance in the randomForest package
...at my response
variable is included along with my predictor variables. That is, I am
getting a MeanDecreaseGini for my response variable, and therefore it seems
as though it is being treated as a predictor variable.
my code (just in case it helps) :
comm.RF<-randomForest(model.data,y=model.data$Comm_Heir,mtry=8,importance=T)
Apologies if it's a stupid question, but I'm new to randomForests. Hopefully
that makes sense and if anyone can let me know how remedy this situation, I
would be so grateful.
Cheers!
[[alternative HTML version deleted]]