Propensity score matching is starting to become common among IR types
who use TSCS data. The studies that I've seen in IR that use it have
done so uncritically. In my dissertation, I use matching on TSCS data
but correct for temporal correlation. One of the assumptions of
matching is that observations are independent. Clearly, most
observations within a panel are not independent. This, in my opinion,
needs to considered, but I'd be interested to hear what others think
as well. I'd be happy to share do-files, the dissertation and a
possible fix for this problem. There is still the problem of
potential spatial correlation, which I do not tackle. The good (bad)
news is that this should affect all data not just TSCS.
Joe
**********************************
Joseph K. Young
Assistant Professor
Department of Political Science
Southern Illinois University
[log in to unmask]
http://mypage.siu.edu/jkyoung
**********************************
On Sep 25, 2008, at 10:46 AM, Carlos Rodriguez wrote:
> Dear list,
>
> I have the following doubt: is it possible (correct) to do matching
> with time-series cross sectional data? I have only seen it used with
> panel (cross-sectional) data.
> thanks
>
> carlos
>
> **********************************************************
> Political Methodology E-Mail List
> Editors: Melanie Goodrich, <[log in to unmask]>
> Delia Bailey, <[log in to unmask]>
> **********************************************************
> Send messages to [log in to unmask]
> To join the list, cancel your subscription, or modify
> your subscription settings visit:
>
> http://polmeth.wustl.edu/polmeth.php
>
> **********************************************************
**********************************************************
Political Methodology E-Mail List
Editors: Melanie Goodrich, <[log in to unmask]>
Delia Bailey, <[log in to unmask]>
**********************************************************
Send messages to [log in to unmask]
To join the list, cancel your subscription, or modify
your subscription settings visit:
http://polmeth.wustl.edu/polmeth.php
**********************************************************
|