Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Christopher Baum <kit.baum@bc.edu> |
To | "<statalist@hsphsun2.harvard.edu>" <statalist@hsphsun2.harvard.edu> |
Subject | Re: st: RE: GMM estimation: restricting parameter estimates |
Date | Thu, 6 Jun 2013 07:43:48 +0000 |
On Jun 6, 2013, at 8:33 AM, Mark wrote: > You could try a variation on a trick that is sometimes used in code to restrict the range of parameter values. Instead of estimating a and b you could estimate 1/a and 1/b. Or some other function that prevents Stata (not "STATA" btw) from deciding on exact zeros as solutions. > > For an example of how official Stata code does something similar, have a look at the manual entry for -heckman- and in particular the discussion of how rho is estimated. There is also a useful FAQ that discusses this sort of trickery. Kit Kit Baum | Boston College Economics & DIW Berlin | http://ideas.repec.org/e/pba1.html An Introduction to Stata Programming | http://www.stata-press.com/books/isp.html An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html http://www.crup.com.cn/Item/111779.aspx * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/