See the paper:
Lechner, M. (2000), "Programme Heterogeneity and Propensity Score
Matching: An Application to the Evaluation of Active Labour Market
Policies," Review of Economics and Statistics, 84, 205-20
for an example. I think you could estimate the appropriate propensity
score for each pairwise comparison using a MNP or MNL, and then input
that p-score variable directly into the psmatch2 command to do what you
want. Alternatively, Lechner compares the results to a model estimating
individual pairwise probits to generate the p-scores, and if I recall,
the results were not overly sensitive. If that's the case, using
psmatch2 for each pairwise comparison may be sufficient.
Dann
****************************************************
Daniel L. Millimet
Associate Professor & Director of Undergraduate Studies
Department of Economics
Box 0496
SMU
Dallas, TX USA
phone: 214.768.3269
fax: 214.768.1821
web: http://faculty.smu.edu/millimet
****************************************************
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of [email protected]
Sent: Sunday, August 20, 2006 5:08 PM
To: [email protected]
Subject: st: Multinomial Propensity Score
I want to compute Propensity Score using multinomial logit/probit
approach. I
need to compare multiple groups. I contact Stata support people and
they told
me that Stata cannot handle it. I tried some ado-files (pscore,
psmatch2 and
sensatt) and I bought the Stata Journal (2002, V2, N4), but it is
presented
just the binomial approach (for a control and single treatment). I will
appreciate if someone can give me some advice about it.
Thanks,
asilva
--
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
