re: st: Stata 9.2 vs limdep

[Christopher Baum <baum@bc.edu>]

<>
While I have no additional information to provide on the Stata-v- 
LIMDEP results, I find some useful suggestions in David Roodman's "How  
to do xtabond2" (Stata Journal 9:1, preprint available from SUG  
archives) regarding the choice of the GMM-difference vs GMM-system  
estimator:

6. Before using system GMM, ponder the required assumptions. The  
validity of the additional instruments
in system GMM depends on the assumption that changes in the  
instrumenting variables are uncorre-
lated with the fixed effects. In particular, they require that  
throughout the study period, individuals
sampled are in a kind of steady-state, in the sense that deviations  
from long-term values, controlling
for covariates, are not systematically related to fixed effects.

(p. 43 of 2006 working paper)

It might be reasonable to ponder whether these conditions are at all  
reasonable in your context before trying to compute the bounds.

Kit

Kit Baum   |   Boston College Economics and 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/