|
|  |
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Binary logit regressions with panel data: How to test equality of regression coefficients?
At 03:24 AM 1/27/2007, Maarten buis wrote:
--- Not Displayed <[email protected]> wrote:
> I am a new user of Stata. I am running binary logit
> regressions on panel data, with random effects. I run
> the same regression for two samples. I would like to
> test if the regression coeeficient on one of the
> variables is equal in these two regressions.
There was recently a discussion on statalist on this issue. The thread
started with
http://www.stata.com/statalist/archive/2007-01/msg00752.html .
(Warning: you are not going to be happy with the answer.)
Hope this helps,
Maarten
Actually, this is a bit different this time. Before, we were talking
about comparing coefficients across nested models, e.g. model 1 has
x1 x2 x3 and model 2 has x1 x2 x3 x4 x5 and you want to compare the
coefficients. In this case, we are talking about a model with x1 x2
x3 that has been estimated on 2 different groups. That is the sort
of thing that can be estimated with a location/scale aka
heterogeneous choice model. The user-written -oglm- can do
that. But, there is an additional wrinkle in this case in that we
are talking about panel data with random effects! So, I am not sure
what to do - maybe gllamm could do it? Anyway, for more on oglm, see
http://www.nd.edu/~rwilliam/oglm/index.html
If I ever get ambitious, I might try to write xtoglm. But I never do
these panel models myself nor do I understand them all that well.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: [email protected]
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
*
* 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/
