Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: testing IIA assumption in standard MNL

From   "Jun Xu" <>
Subject   RE: st: testing IIA assumption in standard MNL
Date   Sat, 20 Aug 2005 19:24:07 -0500


Jun Xu
Ph.D. Candidate
Department of Sociology
Indiana University at Bloomington

From: SC Wainwright <>
To: "" <>
Subject: st: testing IIA assumption in standard MNL
Date: Fri, 19 Aug 2005 16:46:30 +0100

hello statalist,

i have attempted to use the mlogtest with iia option and hausman option, as well
as the manual hausman code (running 2 regressions) to get the above test
working. mlogtest says "you used the old syntax" of hausman and refers me to

hausman all partial, alleqs

which provides the following output(also when i use drop-down post-est menu);

no coefficients in common; specify equations(matchlist)
for problems with different equation names.

i've subsequently tried matching each category and had no luck

'Child' found where integer expected but when using integers, these are not
recognised and giving output "equation Child not found r(111);"

hausman all partial, equations(1:2)
equation at not found

i have a numeric floating 3-category dep var with "Child in school" "Child at
home" and "Child works"

shall i rename dependent variable ?


* For searches and help try:
Express yourself instantly with MSN Messenger! Download today - it's FREE!

* For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index