Re: st: ivreg2 endogeneity test

[Cordula Stolberg <cs32@sussex.ac.uk>]

Kit,

Thanks for that reference.

Cordula

--On 12 August 2004 17:36 -0400 Kit Baum <baum@bc.edu> wrote:

> Cordula wrote:
>
> I now have a question on the endogeneity test with -ivreg2-. I know that
> one can use the Hausman test. i.e. running the regression first with the
> instruments, then running the regression treating all variables as
> exogenous and then doing the Hausman test.
>
> I now read in an earlier posting that it is also possible to use the
> -orthog- option to test for endogeneity, i.e. if I suspect y2 to be
> endogenous:
>
> ivreg2 y1 y2 ( = x4 x5) x1 x2 x2, orthog(y2)
>
> Is this procedure of testing for endogeneity of y2 equivalent to using the
> Hausman test?
>
>
> Please see our Stata Journal paper, which discusses the relation between
> these tests and Durbin-Wu-Hausman tests. A preprint is also available
> from IDEAS (http://ideas.repec.org) via
> http://ideas.repec.org/p/boc/bocoec/545.html
>
> Thanks
> Kit
>
> *
> *   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/



*
*   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/