st: Cox proportional hazard modeling question -- incremental increase in predictor tied to survival times

[Andrew Kim <AKim@evolvondemand.com>]

Hi All,

I have a modeling question using cox proportional hazard models (stcox).  

I am trying to run a cox proportional hazards model to predict the survival of post-op patients grouped by "# of different doctors seen".  Anytime a patient sees a different doctor in a post-op check-up, I increment the "doctors seen" variable up by one.  Some patients see one doctor and others see 10 different doctors in the data.  However, I'm having difficulty modeling around the fact that the # of different doctors seen is a function of survival time (i.e. - the longer you have survived the more opportunity you're given to see different doctors).

Does anyone have any experience with this and possible modeling methods around this?

Please let me know if I can clarify anything above.

Thanks!
Andrew




*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/