Hello listusers,
I would like to test the equivalence of the estimates
using reg3 for subsamples. Two of the endogenous
variables are suspected to have different impacts for
subsamples based on an exogenous variable. Can I test
the equivalence of the estimates by creating dummy
interactions in reg3? Will the following be proper
specification?
Eqn 1: y1 = f(D1*y2, D2*y2, D1*y3, D2*y3, exogenous
variables), where D1=(1,0) and D2=(0,1)
Eqn 2: y2 = f(y1, y3, exogenous variables)
Eqn 3: y3 = f(y1, y2, exogenous variables)
Test: D1*y2 = D2*y2, and D1*y3 = D2*y3,
Alternatively, if the above is not proper, does Stata
have a function that I can estimate the two subsamples
separately using reg3 and test the equivalence of the
estimated coefficients?
Any help will be greatly appreciated.
Best,
Christine
__________________________________________________
Do You Yahoo!?
Tired of spam? Yahoo! Mail has the best spam protection around
http://mail.yahoo.com
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
