[R] R question about prediction from a fitted model

David Winsemius dwinsemius at comcast.net
Sat Apr 26 23:21:58 CEST 2008

Lisa <sangwl at gmail.com> wrote in
news:81f4248d0804252201w1398d678la7d998ba32f5539d at mail.gmail.com: 

> Hi Jorge,
>  ... the new question is,
> is there any prediction for the cox model? I tried
> predict(Surv(y~x),newdata), it only gave the fitted values. Any clue
> on this? thanks a lot! 

I cannot claim great expertise in this area, but my impression is that a 
Surv() objects is not really a Cox model, but rather an object that can 
be an argument to one of the Cox PH functions. Suggestion: construct an 
example and remember to specify which of the libraries the Cox function 
came from.

David Winsemius

More information about the R-help mailing list