st: GMM

[Kit Baum <baum@bc.edu>]

There is no general GMM procedure in Stata, although there are  
certainly other procedures (e.g., xtabond, xtabond2) which implement  
a GMM estimator.

Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html


On Dec 15, 2005, at 2:07 AM, Shakill Hassan wrote:


> Could you please let me know if it is possible to get Stata to  
> compute GMM
> estimates without having to list the instrumental variables, from  
> which the
> package forms the sample moment condition? i.e. how (and if) can I:  
> write
> the moment conditions directly, specify the parameter names, and  
> get Stata
> to estimate them by minimizing the GMM criterion function?
>
>
> If this is possible, could you recommend where I can get some  
> explanations
> and/or examples a little less cryptic then those in the Stata help  
> file?
>
> In none of the examples in the ivreg2 and ivgmm0 command (help)  
> files is
> there any obvious indication of how one specifies the moment  
> conditions
> (and how to specify what the parameters are). It gives the  
> impression the
> GMM facility in Stata (through ivreg2) is limited to IV estimation.  
> Is there
> no general GMM/optimization procedure where one can get the GMM  
> parameters
> from the moment conditions?
*
*   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/