Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

re: st: psmatch2 - exact matching with mahalanobis metric


From   "Ariel Linden, DrPH" <ariel.linden@gmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   re: st: psmatch2 - exact matching with mahalanobis metric
Date   Wed, 3 Oct 2012 10:34:57 -0400

I suggest that you consider using coarsened exact matching, using -cem- (a
user written program found on SSC). If you specify that the specific
variable should have #0 coarsening, it will produce exact matching on that
variable.

Ariel
Date: Tue, 2 Oct 2012 15:17:42 +0200
From: Vincenzo Mariani <vincemar81@gmail.com>
Subject: st: psmatch2 - exact matching with mahalanobis metric

Dear Users,

I'm trying to implement mahalanobis metric matching using psmatch2,
but I'm not able to exact match on a covariate (say, X). With other
matching algorithms, the propensity score can be appropriately
modified to achieve exact matching, as explained here, for instance:

http://www.stata.com/statalist/archive/2010-09/msg00073.html

In my case, I am thinking to solve the problem by performing a
matching iteration for each value of X.  psmatch2 then gives me, for
each obs, the couple (outcome, _outcome), where _outcome is the
outcome of the counterfactual unit.

Then ATT=mean(outcome)-mean(_outcome) for treated. But how do I find
the appropriate (bootstrap) standard errors?

Any help appreciated.

Many thanks,

Vincenzo

*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index