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]

st: teffects – associated balancing tests and comparison with psmatch2


From   Mai Anh Ngo <maianh.ngo@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: teffects – associated balancing tests and comparison with psmatch2
Date   Wed, 4 Dec 2013 12:27:40 -0500

Dear Statalist users,

I am using the command teffects in Stata 13 to estimate the ATTs after
matching. As said in
http://www.ssc.wisc.edu/sscc/pubs/stata_psmatch.htm, the point
estimate using the probit option when using teffects should be the
same as the point estimate when using psmatch2. However, I did not
find it true for my data. Does anyone have the same experience and
know the reason for the difference between the two commands?

I also wonder whether teffects can do matching with kernel algorithm,
and also  if there is equivalent commands/user-written programs to do
similar tests of balancing properties of the propensity scores and the
matching covariates as the pscore and that comes with psmatch2.

The only related post I found in Statalist is below, but it does not
explain how to test for balancing propensities when using “teffects
psmatch”

http://www.stata.com/statalist/archive/2013-08/msg00547.html

Thank you for your time.

Mai Anh Ngo

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