st: Re: seemingly unrelated regression

[Kit Baum <baum@bc.edu>]

No. What you are describing is a variation of SUR, three-stage least  
squares, available with the -reg3- command. If a variable appears on  
the right hand side of any equation in a set of equations, you do not  
have SURs; you have simultaneous equations, and they must be  
estimated with instrumental variables (2SLS/3SLS) techniques.


Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html


On Jul 12, 2007, at 2:33 AM, statalist-digest wrote:


> If you don't mind, one more question: When using SUR, can we have
> variables being both independent and dependent, ie dependent in one
> equation and independent in another? Ie, can we use it to fit some
> simple structural equation models?
*
*   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/