Re: st: Test for structural break in panel

[Christoph Engel <engel@coll.mpg.de>]

Dear David,

Do you have a theoretical reason to expect that the time trend has a 
kink at one point, for the entire panel? Then you could simply (1) 
generate a dummy that is 1 for all observations after the expected point 
in time (2) control for time, the dummy, and time interacted with the 
dummy. If the interaction term is significant, this shows that there is 
indeed the expected kink.

Christoph

Am 3/10/2012 10:22 AM, schrieb David Ashcraft:
> I am wondering, if someone can help me in how to know the structural break in panel data. I believe I can do that by incorporating dummy variables in my regression. Unfortunately, I am running a probit regression and dummy year variables are almost same for each year resulting in omitting variables. I have looked in the previous posting and found the following:
>
> http://www.stata.com/statalist/archive/2008-09/msg00783.html
>
>
> I believe, this is quite common analysis with panel data. There may be some command/user written program that can help me with this.
> I shall really appreciate any support
> Regards
>
>
> David
>
> *
> *   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/


--
_________________________________________________________________
Prof. Dr. Christoph Engel
Max-Planck-Institut zur
Erforschung von Gemeinschaftsgütern
Max Planck Institute for Research on Collective Goods
Kurt-Schumacher-Strasse 10
D 53113 Bonn
Tel. +49/228/91416-10
Fax +49/228/91416-11
e-mail:engel@coll.mpg.de
http://www.coll.mpg.de
http://www.coll.mpg.de/engel.html
http://ideas.repec.org/e/pen22.html
http://papers.ssrn.com/sol3/cf_dev/AbsByAuth.cfm?per_id=251559
_________________________________________________________________

*
*   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/