I am using the ivprobit command and wondering whether there are
packages for implementing the Durbin-Wu-Watson, Hansen, or Sargan test
of the endogeneity of regressors, and if not, whether someone can
suggest a work-around. All of these tests are easily implemented with
the 2sls command, but I am having trouble finding them for the
ivprobit. It's my sense that I should be able to run the same tests
for the ivprobit because the linear index is similar and error term is
presumed to have the same distribution in both models. Any thoughts?
Thanks, in advance, for your help/advice.
Best,
Cullen
--
Cullen Hendrix, Ph.D.
Assistant Professor
Department of Political Science
University of North Texas
http://cshendrix.wordpress.com/
"The machine does not isolate humanity from the great problems of nature,
but plunges it more deeply into them."
Saint-Exupéry, Wind, Sand, and Stars
*
* 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/
