st: tvc option in stcox

["Sudhinaraset, May" <msudhina@jhsph.edu>]

Hello,

Someone else had asked the following question, and I am still a little unclear as to the answer, which I think is important: 

> (1)  How do you choose the best multiplier for the time-varying
> covariates (with -texp(exp)-)?  How do you know if ln(t) is better
> than t?

Given that you did the log-rank test for "drugclass" I assume that
those drugclass variables are binary, not continuous? The  -texp(exp)-
option is for continuous time varying covariates. In case of
categorical variables, I would do spell splitting with -stsplit-.

To ascertain the best multiplier for the time-varying covariates, is one way to look at Schoenfeld's residual with a lowess curve and fit of the data?

xi:stcox ruralnative ruraltourban urbantourban female alcohol i.wlthind3 i.schooljob i.famstruc, nolog noshow schoenfeld(sch*) scaledsch(sca*)
 
stphtest, log plot(ruralnative)

Are you looking for a linear relationship in this instance for the lowess curve to signify texp(_t) vs texp(ln(_t))? Are there other ways to graph this to see the best multiplier for time-varying covariates? 

Thanks,
May

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