Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Austin Nichols <austinnichols@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: Propensity Score Weights in Oaxaca |
Date | Wed, 21 Jul 2010 12:29:55 -0400 |
Ingo Isphording <Ingo.Isphording@rub.de> : I cannot confirm this behavior; this runs for me: ssc inst oaxaca use http://pped.org/lalonde, clear egen p=mean(t), by(black hisp marr) g w=cond(t,1-p,p) oaxaca re78 age educ [iw=w], by(t) relax weight(0) oaxaca re78 age educ [pw=w], by(t) relax weight(0) but I doubt this approach will do what you want anyway; it certainly does not "control for pre-treatment heterogeneity in unobservables" On Wed, Jul 21, 2010 at 2:14 AM, Ingo Isphording <Ingo.Isphording@rub.de> wrote: > Hi all, > > i have a small problem with the oaxaca command. I try to use weights > from a probability score matching with psmatch to control for > pre-treatment heterogeneity in unobservables. Unfortunately, oaxaca > does not accept my weights. I either get : > > oaxaca depvar expvars [iweights=psweight] , > by(treatment_group) relax weight(0) > > weights not allowed > > r(101); > > or: > > oaxaca depvar expvars [iw=psweight] , by(treatment_group) > relax weight(0) > > (model 1 has zero variance coefficients) > > iweight=psweight invalid name > > r(198); > > I am not sure whether it is just a syntax problem, or if I am doing > something wrong. Any suggestions? > > Cheers, > > Ingo * * 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/