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
From
<[email protected]>
To
<[email protected]>
Subject
RE: st: Propensity Score Matching
Date
Wed, 29 Feb 2012 07:58:14 -0500
Marco- Thanks for the feedback.
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Marco Ventura
Sent: Wednesday, February 29, 2012 2:38 AM
To: [email protected]
Subject: Re: st: Propensity Score Matching
Misspecification problems have nothing to do with bootstraping.
Bootstraping is required when the sample is too small and you do not
rely on the closed form for computing the SE of the ATT.
Moreover, as far as I can see from your output the ATT is not
significant and it will not become significant by simply bootstraping.
Finally, beware when using psmatch2 because it does not check for the
balancing to hold, that means that the balancing must be checked by the
Ichino and friend's routine, pscore.
Regards, Marco
Il 27/02/2012 14:51, [email protected] ha scritto:
> I am new to Stata and propensity score matching. I have 143, 110 control
and
> 5,862 treated in my matched samples. I ran pscore2 to get this.
>
> Once I ran pscore I ran a radius matching method with the following
command:
>
> . attr englleve sch_grp sex_1 rd07leve, comsup boot reps(100) dots logit
> radius(0.0001)
>
> The process has given me:
>
> ATT estimation with the Radius Matching method
>
> Analytical standard errors
>
>
>
> ---------------------------------------------------------
>
> n. treat. n. contr. ATT Std. Err. t
>
> ---------------------------------------------------------
>
>
>
> 5862 143110 -0.073 0.008 -8.673
>
>
>
> ---------------------------------------------------------
>
> Note: the numbers of treated and controls refer to actual
>
> matches within radius
>
>
>
> The process has now run for 36 hours (MP2 version of Stata 12.1 AMD 2
core,
> WinXP pro 32byte). Should I let it run longer or am I hopelessly lost in
> some computational problem? Or did I miss specify the model?
>
>
> Thanks for your help and advice
> Ted
>
> *
> * 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/
*
* 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/
*
* 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/