st: Re: external instruments with xtabond2

[Joe Bond <joe.a.bond@googlemail.com>]

Dear Statalist,

I am trying to run some regressions using the xtabond2 command for
difference GMM estimation. I have an endogenous explanatory variable
in my model for which I have found an external instrument; I also have
other endogenous explanatory variables (including the lagged dependent
variable) for which I will need to use internal instruments; and
finally I have a couple of strictly exogenous explanatory variables..

At the moment I am including all endogenous regressors in the gmm( )
section and all exogenous regressors and the extermal instrument in
the iv() section. I was wondering, will this arrangement work as
intended? What I don't quite get is how Stata will know to use the
external instrument for the specific endogenous variable I intend it
to be used for, and also whether I should be putting this variable in
the gmm() section when I want it to be instrumented using the external
variable rather than its own lags. Would I be better off just using
the external instrument on this variable separately beforehand and
then running the xtabond2 command afterwards using the predicted
values from this regression?

Any help would be much appreciated.

Joe
*
*   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/