st: re: GMM and systems of structural equations

[Kit Baum <baum@bc.edu>]

sacrificial faq	

Fausto said

    I have this model:
    y(t)=b0*y(t-1)+b1*X(t)+b2*Z(t)
    Z(t)=a0*Z(t-1)+a1*W(t)

    This model is a panel data with 5 thousands individuals in 10  
years. If
this is not a system, I could estimate for arellano an bond, but the  
problem
arise when I need to use a systems endogenous equations. So, my doubt  
is if
is there a program which it permits to use a arellano and bond and  
systems
endogenous equations for panel estimation?
     Could someone help in this subject?


Estimation of each of these equations with Arellano-Bond (eg  
xtabond2) would be perfectly appropriate. There are no cross-equation  
constraints. It is a common misconception that if you can write down  
a system of equations (in this case a recursive system) you need a  
systems estimator. Systems estimators potentally gain efficiency;  
they are not needed for consistency. "Limited information"  
estimation, that is, estimating each equation separately  with  
xtabond2 -- is just fine here. In the absence of cross-equation  
constraints, you never 'need' to use a systems estimator.



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


*
*   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/