Alvaro,
As far as I know Stata does not have a general GMM routine (to its
embarrasment I would say, even if this could gain me some verbal
spanking in this list).
Maybe you can twist one of the existing routines (e.g. nl) to try to
get at your problem, although my guess is that it is probably easier
(and safer) to you program your own routine from scratch, preferably
in mata.
Otherwise, you would have to look elswere. I know LIMDEP has a general
GMM routine but personally I've never used it so I cannot comment on
it. GAUSS might be another option.
best
robert
On 2/22/06, alvaro <[email protected]> wrote:
> Dear colleagues,
> I need to estimate a non-linear model with gmm.
> the model is of the following type:
>
> y=beta1*y(t-1)+(1-beta1)*(beta2+beta3*x1)+epsilon
>
> with instruments: c x1(t-1) and so on.
>
> Is there any built in facility in Stata to perform this regression?
>
> Cheers,
>
> Alvaro
>
> *
> * 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/
>
*
* 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/
