Luis Aguiar's post asks about stratified propensity score matching. The approach he outlines there is correct as far as it goes. It is incomplete in that he does not describe going on to calculate an overall att--which he could do by averaging the within-strata att, weighting them according to the number of observations in each stratum.
He asks if it can be done in one fell swoop. Check the help file for -psmatch2- and you will find a brief section on stratified matching, with example code. It's essentially the approach he has taken, but all the details are spelled out.
Clyde Schechter
Dept. of Family & Social Medicine
Albert Einstein College of Medicine
Bronx, NY, USA
*
* 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/
