Xiao,
Unless I miss something, this sounds like:
qui streg x1 x2 x3, d(w)
predict surv1, surv
qui streg x1 x3, d(w)
predict surv2, surv
graph surv1 surv2 _t
Another way:
qui streg x1 x2 x3, d(w)
predict surv1, surv
replace x2 = 0
predict surv2, surv
graph surv1 surv2 _t
Amadou.
xiao yi <[email protected]> wrote:
Statalist,
I am doing a survival analysis by fittng a parametric
model. After streg x1 x2 x3, I would like to plot the
survival graphs and do a counterfactual analysis. For
example, if x2=0 (in my original data, x2 is a
continuous variable), what would the survival graph
look like. I think I can run a model by dropping x2
and then plot using stcurve. But how can I put the two
survival graphs together i.e. a specification with x2
and without x2? Thanks.
Xiaoyi
University of Oklahoma
*
* 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/
