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 on April 23, and its replacement, statalist.org is already up and running.


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

st: Dif-in-Dif with year dummy


From   Erasmo Giambona <e.giambona@gmail.com>
To   statalist <statalist@hsphsun2.harvard.edu>
Subject   st: Dif-in-Dif with year dummy
Date   Fri, 13 Aug 2010 12:58:26 +0200

Dear All,

I am estimating an investment model using a panel dataset with yearly
firm data from 1990-2005. My regression model also includes year
dummies (among other controls). My objective is to estimate the effect
of a shock in the banking system on investment using a
difference-in-difference (DD) approach. I have already identified my
control and treatment groups. So, I am OK with this part. I am more
challanged by the change in "policy". When using DD, usually people
look at before and after a policy takes place. In my case, I don't
really have a before/after. I am considering a shock that happened at
the beginning of the year 2000 and was over by the end of the year. My
"policy" change dummy is really a dummy variable equal to 1 for the
year 2000 and zero otherwise. Therefore, my DD estimate is the
coefficient on the interaction on Year 2000 Dummy and Treatment Group
indentifier.

Is this a legitimate way of conducting a DD analysis? Is the
interpretation of my DD coefficient changed by the fact that I am
using a year dummy rather than a true before/after dummy?

I would appreciate any input on the issue.

Thanks,

Erasmo
*
*   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