Ryan,
Date sent: Fri, 3 Oct 2003 13:12:28 -0400 (EDT)
From: Ryan Mutter <[email protected]>
To: [email protected]
Subject: st: Simultaneous Equations
Send reply to: [email protected]
> I am interested in estimating the following equation:
>
> X = a + bY + cM + error
>
> where X, Y, and M are variables and a, b, and c are paremeters to be
> estimated. Y is also determined by X as follows:
>
> Y = d + eX + fD + eM + fZ + error
>
> where Z = D*M.
>
> My question: Can I estimate this system using 2SLS with D, M, and Z
> as instruments for Y?
I think the answer is yes - you can estimate the X equation (not the
system) using 2SLS, treating Y as endogenous and using D and Z as the
excluded instruments. You have one overidentifying restriction, so a
Sargan or Hansen J overidentification test (i.e., a test of
instrument validity) would be a good idea. FYI, ithis is an
automatic output of ivreg2.
--Mark
> My concern is that Z = D*M and M is in the
> first equation.
>
> Thanks.
>
> *
> * 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/
Prof. Mark E. Schaffer
Director
Centre for Economic Reform and Transformation
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS UK
44-131-451-3494 direct
44-131-451-3008 fax
44-131-451-3485 CERT administrator
http://www.som.hw.ac.uk/cert
*
* 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/
