re: st: issues with xtabond2

[Christopher Baum <kit.baum@bc.edu>]

<>
My model originally used fixed-effects estimation but since one of the 
independent variables is a lagged term of the dependent variable, I believe 
I'm violating the strict exogeneity assumptions which is why I was trying to 
use a dynamic panel estimator such as GMM.  Is there another possible 
approach that you can recommend for dynamic panel estimation?


The Anderson-Hsiao estimator, which is an IV approach as well, but uses 'true' lags as IVs.  A-B DPD is a 'better mousetrap" if T is really small, but in your case it is not. help xtivreg or, from SSC, help xtivreg2 (by Mark Schaffer).

Kit

Kit Baum   |   Boston College Economics & DIW Berlin   |   http://ideas.repec.org/e/pba1.html
                             An Introduction to Stata Programming  |   http://www.stata-press.com/books/isp.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/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/