Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | shyam basnet <shyamabc2002@yahoo.com> |
To | STATAlist <statalist@hsphsun2.harvard.edu> |
Subject | st: Heterogeneity in treatment effects |
Date | Thu, 19 Jul 2012 11:39:15 -0700 (PDT) |
Dear Stata Users, I am working on estimating Average Treatment Effect on treated (ATT) using Nearest-Neighbour matching based on the estimated propensity scores. In covariate set, I have a location dummy variable and the other explanatory variables. The data set consists of two different locations but they are pooled into a single data set. I first ran the propensity score model with logistic regression and then estimated a single parameter coefficient of ATT on outcome variables (like yield, cost). It gives me a homogeneous ATT effect for both locations. But I want to test heterogeneity in ATT estimates across locations. My interest here is to do a test exactly same as Chow test in regression analysis, but here in ATT estimates. I would appreciate for your suggestion of any references or literatures. Thanking you, Sincerely Yours, Shyam Basnet Nepal * * 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/