Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Confidence intervals on adjusted STS curves?


From   Kaleb Michaud <kaleb@stanford.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Confidence intervals on adjusted STS curves?
Date   Thu, 27 May 2004 17:37:10 -0700

Is there any work-around for getting 95% point-wise confidence intervals to show up on a survivor function graph that's been adjusted?

There are two ways I see of creating this plot:

Approach #1:
Take the variables you want to use in the hazard model and make new ones such that when they equal 0, this corresponds to the actual value you want them adjusted to. (eg. gen age50 = age - 50) Then perform -sts graph, adjustfor(varlist)-. There's no current way to get confidence intervals on this plot.

Approach #2:
Perform -stcox varlist, basesurv(newvar)-, then plot it using -stcurve, survival at(varname=# varname2=#...)-. Again, the plot doesn't allow a CI band.

Any ideas? Assume my only choice is to manually create these three variables and then -twoway line- graph them? It's somewhat aggravating because I know SAS does this with a straight-forward option, but I'd like to do everything in Stata (ie. I dislike learning too many stat programs).

Thanks!
Kaleb Michaud

*
* 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/




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