Re: st: correct for selection bias in survival analysis

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Wed, 5/5/10, Marguerite Duponchel wrote:
> I am running a loglog survival analysis as such:
> 
> streg duration_event vars, dist(loglog) cluster(y)
> 
> I need to correct for a selection bias in the sample using
> a probit on the probability of the event happening.
> 
> probit event varsbis
> 
> Does anyone know an easier way to correct for a potential
> selection bias that calculating the IMR from the probit
> and introducing it in the survival analysis as an
> explanatory variable?

The trick with including the inverse Mills ratio (I presume
that that is what you mean with IMR) only works in linear
models, so it won't work in survival models. You could 
instead take a look at the -frailty()- option in -streg-.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/