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: Propensity score matching in stata


From   Adam Cheung <adam_kalok@yahoo.com.hk>
To   statalist@hsphsun2.harvard.edu
Subject   RE: st: Propensity score matching in stata
Date   Tue, 24 Jul 2012 17:51:15 +0800 (SGT)

Hi Eilnaz,

As already pointed out by others, I guess you need to tell us more about what you want to do with "matching". Do you want to match firms in order to estimate the effect of issuing debt on some outcome variables? 

"logit debt size industry_type product_type" is a command to run a logistic regression model for you to estimate the propensity of issuing debt for the sampled firms. 

If you really have to match firms (based on propensity of issuing debt) in order to estimate the ATT/ATE, several commands are available in Stata (pscore, psmatch2, nnmatch etc, try to search them and read the help files in Stata). 

If you are not familiar with PSM, you may read:

Caliendo, M., & Kopeinig, S. (2008). Some practical guidance for the implementation of propensity score matching. Journal of Economic Surveys, 22, 31-72.

Stuart, E. A. (2010). Matching methods for causal inference: A review and a look forward. Statistical Science, 25, 1-21.

Or other textbooks on PSM. 

Hope this can help. 

Regards,
Adam


--- 2012年7月24日 星期二,KASHEFIPOUR E. <E.KashefiPour@swansea.ac.uk> 寫道﹕

> 寄件人: KASHEFIPOUR E. <E.KashefiPour@swansea.ac.uk>
> 主題: RE: st: Propensity score matching in stata
> 收件人: statalist@hsphsun2.harvard.edu
> 日期: 2012年7月24日,星期二,下午4:55
> Thanks a lot Shikha. Your comments
> were really helpful.
> Does the command that you gave me "logit debt size
> industry_type product_type" match samples by firms and
> industry? What does this command do?
> 
> Thanks
> 
> 
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> on behalf of Shikha Sinha
> Sent: Tue 24/07/2012 01:52
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: Propensity score matching in stata
>  
> If you want to estimate the average treatment effects (ATE
> or ATT),
> you can use psm. In your case, are you also looking at the
> impact of
> issuing debt on some outcome(?)? if not then, matching is
> not a good
> strategy and simple probit or logit will solve your
> problem.
> 
> logit debt size industry_type product_type
> 
> This model will answer question about which type of company
> is more
> likely to issue debt. Hope it helps.
> 
> Shikha
> 
> On Sat, Jul 21, 2012 at 2:29 PM, KASHEFIPOUR E.
> <E.KashefiPour@swansea.ac.uk>
> wrote:
> > Dear Marco,
> >
> > Many thanks for your help.
> >
> > Actually, I am a new user of PSM, and therefore I
> appreciate if you could let me know about att in more
> details.
> >
> > Best,
> > Eilnaz
> >
> >
> > -----Original Message-----
> > From: owner-statalist@hsphsun2.harvard.edu
> on behalf of Marco Ventura
> > Sent: Sat 21/07/2012 09:21
> > To: statalist@hsphsun2.harvard.edu
> > Subject: R: st: Propensity score matching in stata
> >
> > Dear friend,
> > The propensity score matching estimator is aimed at
> working out the average treatment effect for the treated,
> att, and in its first step it works out the probability of
> being treated, ie of having issued debt in your case.
> Therefore, unless you are interested in the att you do not
> need to use PSM, you may simply run a logit or probit reg.
> Hope this helps.
> > Regards marco
> > ----- Messaggio originale -----
> > Da: KASHEFIPOUR E. <E.KashefiPour@swansea.ac.uk>
> > A: statalist@hsphsun2.harvard.edu
> > Inviato: Fri, 20 Jul 2012 18:23:22 +0200 (CEST)
> > Oggetto: st: Propensity score matching in stata
> >
> >
> >
> > Hi all,
> >
> > I have a concern regarding the propensity score
> matching.
> >
> > I have a list of companies that issue debt between 2007
> and 2011. My aim
> > is to match those companies with those companies which
> have not issued
> > debt between 2007 and 2011 and investigate the
> probability of issuing
> > debt.
> > Can anyone tell me if the propensity score matching is
> an appropriate
> > estimation in my case? If so, which command I can use
> in stata to match
> > those companies with industry and size?
> >
> > Best,
> > ELN
> >
> > *
> > * 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/
> 

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