----- Original Message -----
From: "Robert Bozick" <[email protected]>
To: <[email protected]>
Sent: Thursday, November 06, 2003 8:21 AM
Subject: st: Hausman test for IIA, anyone??
> Hey Stata users -- I posted a question a few days back and haven't heard from
anyone, (which means either no one knows the answer or the message may have
gotten buried in your inbox). In any case, I am reposting it again --- any
help/thoughts are appreciated!
>
> I am having a problem using the Hausman test of independence of irrelevant
alternatives (IIA) following the estimation of a multinomial logistic regression
model. I have a three category nominal dependent variable called DV (0 = no
college, 1 = immediate enrollment in college, and 2 = on-time enrollment in
college).
>
> I first estimate the model:
> mlogit DV x1 x2 x3 x4
>
> STATA estimates the model with no problem. I then use the commands to obtain
the Hausman test:
>
> mlogtest, hausman base
>
> STATA tells me
> **** Hausman tests of IIA assumption
>
> Ho: Odds(Outcome-J vs Outcome-K) are independent of other alternatives.
>
> no coefficients in common; specify -equations(matchlist)- for the problem of
different equation names. r(498);
>
>
> Does anyone know if I am doing something wrong?
>
> Thanks in advance for your help,
> Robert
>
Do you have the most recent version of mlogtest?
. which mlogtest
c:\ado\stbplus\m\mlogtest.ado
*! version 1.6.4 2/11/03 correct hausman problem for Stata 8
Scott
*
* 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/
