st: How to post-estimation after log-binomial regression?

[Mashhood Sheikh <senor_massao@hotmail.com>]

Dear Statalisters,
 
I’m using data from a cross-sectional study (n=12,000), where the outcome(s) are not rare. What I have understood so far (novice PhD student here), that the best approach is to use log-binomial regression in order to get RR estimates. Since the log-binomial regression may not converge, predict propensity scores, and use them in the final model instead of adding 10 covariates in the model.
 
However, I am unaware of the postestimation commands one can use to assess the log-bonomial model? Any feedback is highly appreciated.
 
This is the command I am using to get RR with log-binomial regression.
 
glm Y X Confounders, fam(bin) link(log) nolog eform
 
Thankfully,
Mashhood
---
PhD student, Institute of Community Medicine, 
Faculty of Health,
University of Tromsø,
Norway 		 	   		  
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/