Hi Zi!
On 11/28/09, Yi Du <abraham.du at gmail.com>
wrote:> I'd like to resort generalized methods of moment to estimate a
regression
> model but I can't understand the help file of gmm package. If the
regression
> model is y, the instrumental variable is x, how can I write the code?
>
> By the way, I use systemfit's 3sls with method3sls='GMM', but I
can't get
> the suitable results.
The argument "method3sls" of systemfit is only relevant for
three-stage least-squares estimations (i.e. argument "method" is
"3SLS"). Currently, systemfit cannot estimate models by GMM.
Best,
Arne
--
Arne Henningsen
http://www.arne-henningsen.name