Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Ologit question

From   "Anat (Manes) Tchetchik" <>
Subject   Re: st: Ologit question
Date   Wed, 31 Oct 2012 21:40:37 +0200

Thanks Jay, I really appreciate your help

On Wed, Oct 31, 2012 at 8:47 PM, JVerkuilen (Gmail)
<> wrote:
> On Wed, Oct 31, 2012 at 1:44 PM, Anat (Manes) Tchetchik
> <> wrote:
>> Thanks,  I ran the Brant test of parallel regression assumption and it
>> turned out insignif. (p>chi2=0.877) does it supprt the use of ologit?
> Not if asymptotics themselves don't apply, though it's hard to say
> here. The real problem is that you have a lot of IVs for your sample
> size.
>> Also- what is the main difference between the ologit and rologit? The
>> data I have  actually refer to 3 groups of 50 observations each
>> (cardiology, oncology and orthopedic) I currently used dummy vars. to
>> control for this, maybe the ranked ordered logit is more appropriate?
> -rologit- is for responses that are ranked. It fits the Plackett-Luce
> model. This is used when a respondent has multiple objects and ranks
> them, and would thereby be giving multiple responses. So if each
> respondent were to be asked "what medical speciality do you intend to
> study for? rank order them" then yes -rologit- is more applicable.
> Jay
> *
> *   For searches and help try:
> *
> *
> *

Anat Tchetchik, PhD
Department of Hotel and Tourism Management
Guilford Glazer Faculty of Business and Management
Ben-Gurion University of the Negev
P.O.Box: 653
Beer-Sheva, Israel, 84105

Phone         972-(0)8-6479735
Fax:           972-(0)8-6472920
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index