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, statalist.org is already up and running.


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

Re: st: Ologit question


From   "JVerkuilen (Gmail)" <jvverkuilen@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Ologit question
Date   Wed, 31 Oct 2012 12:59:55 -0400

On Wed, Oct 31, 2012 at 10:09 AM, Anat (Manes) Tchetchik
<anatmanes@gmail.com> wrote:
> No,  I have no weighting term and havn't drop any case (I have 148 obs.)

Ah, from looking at your model you have a lot of variables for the
number of cases and asymptotic tests may be dubious even if they are
syntactically correct. Given that the thresholds are reasonably
symmetric you might want to try a few different merges of the
categories and use logit or even run linear regression with
bootstrapped standard errors. The distribution looks like it's
reasonably symmetric from the ologit cutpoints. Even if you intend to
keep the ologit model in the end, checking from a few different angles
won't hurt.
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index