9
$\begingroup$

I'm trying to use the randomSurvivalForest package in R to predict the next event in a series of events (using res <- predict(fit,v)), but all I get is a total % survivors and then the cumulative hazard for each individual in the res$ensemble. Can I use this to predict/generate values matching what's in in res$time?

$\endgroup$
1
  • $\begingroup$ Or is there some other time series prediction package for repeated events that better to use for this kind of problem? $\endgroup$
    – sunkencity
    Commented Aug 30, 2011 at 15:57

1 Answer 1

1
$\begingroup$

As you descibe it with:

next event in a series of events

It seems like you will definately want to look into time series analysis, perhaps an arima class model can provide you with some good results.

$\endgroup$

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.