[R] coxph fails to survfit

[Bond, Stephen]

Responding to T. Therneau:

> sessionInfo()
R version 2.10.1 (2009-12-14) 
i386-pc-mingw32 

locale:
[1] LC_COLLATE=English_United States.1252  LC_CTYPE=English_United States.1252    LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C                           LC_TIME=English_United States.1252    

attached base packages:
[1] splines   stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] survival_2.35-8

Also:
> s1 <- predict(mod1,newdata=inc[50050:50100,],
+               type="expected")
Error in predict.coxph(mod1, newdata = inc[50050:50100, ], type = "expected") : 
  Method not yet finished


Stephen 

-----Original Message-----
From: Terry Therneau [mailto:therneau at mayo.edu] 
Sent: Friday, February 04, 2011 8:54 AM
To: Bond, Stephen
Cc: r-help at r-project.org
Subject: Re: coxph fails to survfit

>  I have a model with quant vars only and the error message does not
make sense:

Could you tell us what version of S and of the survival package you are
using?  You can get this with sessionInfo(), see the posting guide for
details.  

This would help me identify the issue.  I was planning to post an update
to CRAN this weekend that has changes to survfit.coxph, addressing a
different issue than yours  -- models with a strata by covariate
interaction --- but this would be a very good time to address your issue
too if it is a code bug.

Terry Therneau (author of survival).