Re: st: Chow test as a solution for testing of equality of coefficients across two separate samples.

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Tue, 22/6/10, natasha agarwal wrote:
> I wanted to test the equality of a coefficient across two
> different groups namely developed and developing.
>
> So for example when I estimate
> 
> xtreg lnrval lnk lnw lnvfdi lnvfdi*D y14-y18, fe
> vce(robust)
> 
> where D=1 if developed and zero otherwise.
> 
> a significant coefficient on lnvfdi*D will tell me the
> difference in the impact of FDI when the country is developed.
> 
> But can one conclude that coeffcient on lnvfdi minus
> coefficient on lnvfdi*D is the actual impact of FDI when country is
> developed?

First of all you need to include D as a covariate.

The coeficient of lnvfdi is the effect of lnvfdi in developing
countries
The coefficient of lnvfdi*D is the difference in effect of
lnvfdi in developing and developed countries
The effect of lnvfdi in developed countries is thus the sum
of the coefficients of lnvfdi and lnvfdi*D

See, e.g.:
http://www.stata.com/statalist/archive/2005-02/msg00779.html

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/