Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: R: Estimating the probability of censoring


From   Michael McCulloch <mm@pinest.org>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: R: Estimating the probability of censoring
Date   Fri, 26 Sep 2008 08:54:14 -0700

Antoine Terracol made the brilliant suggestion of estimating probability of censoring, based on -stcox- with specifying the baseline hazard option basechazard(). In studying the manual (v9, page 147) section on the Technical Note for Example 7 of -stcox-, I read that specifying the baseline hazard option requires all variables to make sense if they would be equal to zero (which of course would not be the case with a variable such as age). That makes sense to me.

At the bottom of that page, I read that this can be resolved by subtracting mean age from each subject's age. Is this what is referred to as "centering on age"?
Michael



Antoine Terracol wrote:
Michael,

What is calculated here is the survival function at time t conditional on covariates, i.e., in your case, the probability that the subjects time-to-censoring will be greater than t if dying from cancer was not a risk.
Of course, this is because Michael specified

. stset studytime, failure(died==0)

i.e. he is modelling time-to-censoring instead of the usual time-to-failure.

Antoine
*
*   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/
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index