Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Nominal or ordinal?
From
Richard Williams <[email protected]>
To
[email protected], [email protected]
Subject
Re: st: Nominal or ordinal?
Date
Thu, 12 Aug 2010 21:05:07 -0500
At 07:38 PM 8/12/2010, Clive Nicholas wrote:
In addition to the excellent responses given, with which I concur, you
could treat the variable as multinomial, regress it onto your
independent variables by fitting -mlogit-, and then test the IIA
assumption with the user-written -mlogtest- (downloadable via STB:
-net stb 58 sg155-). If the IIA is violated, then you might consider
combining a couple of the indicators of your response variable before
running it through -ologit- or -oprobit-. Then again, you might think
of all this as rather too exotic.
I didn't realize that -mlogtest- was originally an STB program. I
don't know if it has changed much over the years, but the most
current version is contained in -spost9-, available on Scott Long's
web site. ( -findit spost9- ). The spost9 suite has a lot of other
useful programs, including -brant-, which tests whether the
assumptions of the ordered logit model are violated.
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/