Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

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

From |
Michael Boehm <michael.boehm1@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: Test of parameter equality between two seemingly unrelated regressions |

Date |
Wed, 15 Feb 2012 19:46:00 +0000 |

On Wed, Feb 15, 2012 at 3:40 PM, Maarten Buis <maartenlbuis@gmail.com> wrote: > On Wed, Feb 15, 2012 at 4:25 PM, Michael Boehm wrote: >> I want to run two seemingly unrelated regressions and then test for >> the equality of coefficients for two of the subregressions, ie >> >> sureg (dd t1 t2) (w t1 t2) if sample== 0 >> sureg (dd t1 t2) (w t1 t2) if sample== 1 >> >> and then test whether the coefficient for t1 in the regression of w on >> t1 and t2 is the same in the two samples. > > sureg (dd i.sample##(c.t2 c.t2) ) (w i.sample##(c.t1 c.t2)) > > The interaction effect for sample and t1 in the w equation gives you > the difference in effect of t1 between sample 0 and sample 1. > Similarly for the interaction between sample and t2. The test > statistics next to these interaction effects are for the test that > these differences are 0, so that is what you are looking for. > > Hope this helps, > Maarten > > -- > -------------------------- > Maarten L. Buis > Institut fuer Soziologie > Universitaet Tuebingen > Wilhelmstrasse 36 > 72074 Tuebingen > Germany > > > http://www.maartenbuis.nl > -------------------------- > > * > * 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/ Hi Maarten, That's a very nice way of doing it. Thanks a lot for this. One question aside: do you---or anyone else on the list---know how to adress the interaction term for some postestimation testing, eg. if I want to test whether the difference between coefficient of t1 and t2 on w is different in the two samples. The following 'naive' way test [w]sample #c.t1 - [w]sample #c.t1 = 0 gives me the error message '[decade#c.t1] not found'. Thanks again, Michael * * 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/

**References**:**st: Test of parameter equality between two seemingly unrelated regressions***From:*Michael Boehm <michael.boehm1@gmail.com>

**Re: st: Test of parameter equality between two seemingly unrelated regressions***From:*Maarten Buis <maartenlbuis@gmail.com>

- Prev by Date:
**st: Estimating a dynamic limited dependent variable model (xtabond)** - Next by Date:
**RE: st: xtabond2 for 2 DVs?** - Previous by thread:
**Re: st: Test of parameter equality between two seemingly unrelated regressions** - Next by thread:
**st: Estimating a dynamic limited dependent variable model (xtabond)** - Index(es):