re:Re: st: No valid instruments for system GMM

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

<>
I estimated the same model with the difference GMM, and the Hansen test passes with laglimits set at 16 and i get much better results.

I am very new to the GMM estimator and don't know if this is the right place to ask about this, but what exactly does the GMM-style instrument option laglimits(a b) (mentioned in xtabond2) mean. And what happens if I don't specify it?

For example does

 xtabond2 y l.y x1 x2 x3 x4 x5, robust gmm(l.y x4 x5, lag(16 17)) iv(x1 x2 x3)

mean that at maximum yt-1 is instrumented by yt-16 ?


Suggest you read through David Roodman's "How to do xtabond2" before using the routine further...  laglimits(16 17) mean that ONLY the 16th and 17th lags are used as (really lousy) instruments.

See

http://ideas.repec.org/a/tsj/stataj/v9y2009i1p86-136.html
or, if you don't have access to SJ,
http://ideas.repec.org/p/boc/asug06/8.html

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/