[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: gologit2

From   Richard Williams <>
To, <>
Subject   RE: st: gologit2
Date   Tue, 15 Apr 2008 15:16:43 -0500

At 05:54 PM 4/14/2008, Verkuilen, Jay wrote:

I hope no one misunderstands me on this point: The generalized model is
very useful but I think giving up the proportional odds assumption in
the face of "small but significant" violations is a bad idea. It's kind
of like taking the goodness of fit statistics in SEM or confirmatory
factor analysis too seriously.... If the violations are real, that's a
totally different question.
I certainly agree. Especially with large data sets, with just about any method you're bound to find that one assumption or another is technically being violated. Whether the violation is substantively important enough to worry about is another matter.

One caveat though, and this goes well beyond gologit2: researchers often justify using simpler and easier methods because effects have the same sign and statistical significance as in the more appropriate and more complicated methods. If all you care about is sign and significance though, you might as well use ols regression rather than ordinal or binomial methods. The fact that conclusions about sign and statistical significance tend to be the same across very different methods does not mean that the substantive implications of different methods are the same.

Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: Richard.A.Williams.5@ND.Edu

* For searches and help try:

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