st: Controlling for selection bias in hazards regression models

[Eleonora Paesen <eleonora.paesen@googlemail.com>]

Hello,

Is there a way in stata to control for a sample selection bias in
hazards regression models?
I am currently applying a Cox proportional hazards model to look at
the impact of employment career factors on childbearing. I first carry
out my analyses on the original unrestricted sample and in a second
stage I restrict my analyses on women who had at least an episode of
employment in my observation window as I interested in a set of
employment careers indicators. Is there a way to control for a sample
selection effect in Stata (I have in mind something like Heckman's
two-stage regression method)?
Any help would be greatly appreciated.
Best,
Eleonora
*
*   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/