Re: st: Propensity Score Matching

[David Kantor <kantor.d@att.net>]

I would reiterate what one other responder wrote: that this request 
is too vague to give any specific advice.

But in addition to -psmatch-, which was already mentioned, you might 
consider -mahapick-, which includes several programs to generate a 
propensity score in various different ways.
-ssc desc mahapick-.

(mahapick is expected to get an update soon, but for only minor 
changes to existing programs.)

HTH
--David

At 03:27 PM 2/18/2012, you wrote:
> Dear Statalisters,
>
> i want to use Propensity score matching method to identify firms which has
> similar characteristics suggesting them to use X item and the only
> difference between these firms is their actual use of X item. I am using K
> nearest matching method. Now after identifying firms i want to do a Matched
> Sample Test
>
>        X item Users           X item Non Users
> N   Mean Median            Mean Median            Diff in Mean
>
> Could anyone please tell me how can i do this?
>
> Regards,
> Vikram

*
*   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/