Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: GMM in Stata 11: how to include moments without instruments


From   "Brian P. Poi" <bpoi@stata.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: GMM in Stata 11: how to include moments without instruments
Date   Mon, 16 Nov 2009 08:01:24 -0600 (CST)

On Fri, 13 Nov 2009, Anna Blank wrote:

Hello,

I have a problem understanding how -gmm- works in Stata 11 in the
cases when no instruments should be specified.
In particular, if I have to estimate a population moment, such as the
variance, from sample moments.

The GMM command in Stata should be able to do this as well as estimate
models require instruments. Does anyone have a suggestion for way of
implementing this using the -gmm-?


Just don't specify the instrument() option.  Without the instrument()
option, -gmm- uses just a constant as the only instrument, which allows you to fit moment conditions of the very general form E[h(data; parameter)] = 0. In that case, the number of moment equations must be at least as great as the number of parameters.

  -- Brian Poi
  -- bpoi@stata.com


*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index