On Wed, Oct 31, 2012 at 9:23 AM, Anat (Manes) Tchetchik
<anatmanes@gmail.com> wrote:
> Dear statalist,
>
> Sorry for the probably trivial question
> I ran an Ologit and received the following cutoffs:
>
> Coef. Std. Err. 95%
> Conf. Interval]
> /cut1 | -1.798009 2.900799 -7.483471 3.887453
> /cut2 | .7973023 2.793147 -4.677166 6.271771
> /cut3 | 2.902347 2.794626 -2.57502 8.379713
> which means that the cutoffs are not significantly different.
> Does it mean that the entire model is worthless?
Before you jump to any conclusions about the machine not working make
sure that the cord's plugged in. Did you forget a weighting term or
did listwise deletion dump most of your cases? Standard errors of
these cutoffs should be proportional to 1/sqrt(n) and these are huge.
Usually what happens with a crappy model is that the terms end up not
separated, but that's not what you have here.
*
* 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/
