[R] Time interactions for coxph object

David Winsemius dwinsemius at comcast.net
Tue Apr 8 05:41:25 CEST 2014

On Apr 7, 2014, at 9:36 AM, Tim Marcella wrote:

> Hi All,
> I am working in the 'survival' library and need to know how to code a
> variable time interaction for left truncated data (not all subjects
> followed from the start of the study). I therefor add in the entry  
> time and
> exit time variables into the formula.
> Here is my basic formula
>    CSHR.shore.fly <- coxph(Surv(entry, exit, to == 1) ~ shore.cat,  
> data
>      glba.mod)
> My variable shore.cat is violating the proportional hazards  
> assumption so I
> am trying to add in an interaction with time. Do I interact exit?  
> entry? or
> the range of the two?

If you believe there is a trend in risk then there is the 'tt'  
argument which takes a function.

David Winsemius, MD
Alameda, CA, USA

More information about the R-help mailing list