[R] survival analysis using rpart

Terry Therneau therneau at mayo.edu
Tue Feb 27 16:30:09 CET 2007


> I use rpart to predict survival time and have a problem in interpreting the
> output of ?estimated rate?

> (1) Is the ?estimated rate? the estimated hazard rate ratio? 
> (2) How does rpart calculate this rate?
> (3) Suppose I use xpred.rpart(fit, xval=10) to perform 10-fold
> cross-validation using (a) the complete stagec data set and (b) only a
> subset of it, say, using the columns Age, EET, and G2 only. For the i-th
> patient, I am likely to obtain a different estimated rate. How can I
> meaningfully compare both rates? How can say which one is ?better?? 

For questions 1 and 2, you need to read the documentation.
   www.mayo.edu/biostatistics , get technical report #61.  (We should bundle
 this with the package, I suspect)
    or the appropriate chapter in Venables and Ripley, Modern Applied Statistics
 with S, 4th edition.
 
 For question 3, rpart does not have the usual "nested model" likelihood
 ratio tests. I don't know how to say which model is better.
 
 	Terry Therneau



More information about the R-help mailing list