Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

Re: st: Propensity score matching: confidence intervals


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Propensity score matching: confidence intervals
Date   Tue, 26 Jul 2011 16:47:02 -0500

On Tue, Jul 26, 2011 at 11:50 AM, Ariel Linden. DrPH
<ariel.linden@gmail.com> wrote:
> As PSMATCH2 uses regression to derive those estimates, you can do the same
> manually. In fact, I'd suggest you add robust or cluster SE's (cluster on
> pair ID). PSMATCH2 creates all the variables you'll need to run the
> regression.

I would then suspect that these standard errors are too small, in that
they don't account for the fact that some of the regressors were
generated. There was an influential paper by Murphy and Topel (1985,
JBES, http://www.citeulike.org/user/ctacmo/article/816962) on the
issue, and the later elegant solution by Hardin (2002, Stata Journal,
http://www.citeulike.org/user/ctacmo/article/4735885) that show how to
overcome the issue.

-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.
*
*   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/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index