I am estimating a Cox model that includes several variables both alone and as time-dependent covariates (interaction terms with time), e.g:
stcox age race elixS1 elixS2 admsS1 admsS2, tvc(age admsS1 admsS2) texp(ln(_t))
and I want to use -adjust-. But, since the Hazard for age, admsS1 and admsS2 are now time-dependent, I'll need to look at the Hazard for several different values of time (or ln(_t) actually), but I cannot figure out from the manual how to do this. When I put a value of _t or ln(_t) into the syntax of -adjust- (just as I would to set the value of any other variable in a model before using adjust) I get an error message.
So, my question is, can I do this, and if so how?
Thanks.
Allan
*
* 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/
