--- Jayme Sar <[email protected]> wrote:
> I want to estimate a conditional logit for a discrete choice problem,
> and I need to make sure that the results are consistent for all
> subsamples in the population.
>
> In other words, I want to do something like:
>
> clogit y x1 x2
>
> for all 1000 observations.
>
> and:
>
> clogit y x1 x2 for the first 200 observations.
>
> How do I compare the coefficients for the full sample (1000 obs) and
> the subsample (200 obs)? Is there something like a Chow test for the
> conditional logit?
what about:
gen d = _n <= 200
gen dXx1 = d*x1
gen dXx2 = d*x2
clogit y x1 x2 d dXx1 dXx2
test d dXx1 dXx2
If the estimates in the first 200 observations are the same as the
estimates in the entire sample then the dummy d and the interaction
terms between the dummy and the other covariates should be zero.
-- Maarten
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
__________________________________________________________
Sent from Yahoo! Mail.
A Smarter Email http://uk.docs.yahoo.com/nowyoucan.html
*
* 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/
