Re: st: discrete time-varying covariate in cox models

["Daniel O. Koralek" <dkoralek@unc.edu>]

Thanks!  I was having a brain freeze there!



Re: st: discrete time-varying covariate in cox models
From
  "E. Paul Wileyto" <epw@mail.med.upenn.edu>
To
  statalist@hsphsun2.harvard.edu
Subject
  Re: st: discrete time-varying covariate in cox models
Date
  Wed, 21 Nov 2007 19:37:05 -0500
Suppose you had 20 event times, and you stsplit your data using a  
variable called timept. Timept would take on values from 0 to 19. If  
you also had a variable for the time at which the screening took place  
(screentime, also =0..19), then you would simply say:

gen screenstatus=screentime>timepoint.

That should do it.

Paul

Daniel O. Koralek
Department of Epidemiology/Lineberger Comprehensive Cancer Center
The University of North Carolina at Chapel Hill
Chapel Hill, NC  27599-7435
http://www.unc.edu/~dkoralek/
dkoralek@unc.edu




*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/