I should make prediction on survival data, using the random Forest method. My question is: should I follow the same approach as in logistic regression? taking into account only the status variable or whether I should take into account the delay to the event? Are there any specific R functions for survival analysis other than randomForest? Or could I use this function for survival analysis as well? I've seen a function called ranger() that seems to do random forest on survival data, but I haven't understood much of it.

  • $\begingroup$ Definitely use survival times and censoring times. There are, of course, the "classical" methods supported by the "recommended" package named: "survival". There's also fairly well-known "randomForestSRC". The ranger package touts its abilities to handle sparse predictors. That would definitely be an important advantage if your data fit that description. $\endgroup$
    – 42-
    Jun 27, 2022 at 23:34


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.