Statalist


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

RE: st: AW: RE: Matching Estimator


From   "Nick Cox" <[email protected]>
To   <[email protected]>
Subject   RE: st: AW: RE: Matching Estimator
Date   Thu, 10 Dec 2009 17:17:04 -0000

Sorry, but I've never worked in this area: I just know some references. Others should be able to help. 

Nick 
[email protected] 

Erasmo Giambona

I found that the two documents are very useful to understand how
Average Treatment Effect (ATE) and AverageTreatment Effect on the
Treated (ATT) are calculated. I couldn't find much guidance though on
when one would use ATE instead of ATT. More specifically, if I am
interested in the effect of education on earnings, which one (ie, ATE
or ATT) is preferable?


On Thu, Dec 10, 2009 at 4:06 PM, Martin Weiss <[email protected]> wrote:
>
> <>
>
> "...leads to a forthcoming paper in Statistical Science"
>
>
> I can already download the paper, and it does feature a section about
> "Matching software for Stata", as well as "Matching software" for Some
> Alternative Software...
>
>
>
> HTH
> Martin
>
>
> -----Ursprüngliche Nachricht-----
> Von: [email protected]
> [mailto:[email protected]] Im Auftrag von Nick Cox
> Gesendet: Donnerstag, 10. Dezember 2009 16:05
> An: [email protected]
> Betreff: st: RE: Matching Estimator
>
> No idea if it's what you're after but
>
> http://www.imstat.org/sts/future_papers.html
>
> leads to a forthcoming paper in Statistical Science
>
> "Matching Methods for Causal Inference: A review and a look forward"
>
> by Elizabeth Anne Stuart.
>
> Nick
> [email protected]
>
> Erasmo Giambona
>
> I am trying to use the Abadie/Imbens (2002) estimator that one can
> obtain with "nnmatch". Can somebody provide some intuition on the
> difference between Average Treatment Effect (ATE) and Average
> Treatment Effect on the Threated? In prticular, what does it mean that
> in the case of the ATE "all observations are matched to their nearest
> m neighbors of the opposite treatment group" (from help nnmatch)? Why
> would one want to match the firms in the control group?
>
> Abadie, A. and G. Imbens. 2002. Simple and Bias-Corrected Matching
> Estimators. Tech. rep., Department of Economics, UC Berkeley.
> http://emlab.berkeley.edu/users/imbens/.

*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index