Re: st: oglm and heterogeneous choice models

["Rourke O'Brien" <rourke.obrien@gmail.com>]

Gotcha. That makes sense. I was trying to find another way to diagnose
which variables predict residual variance since using “sw, pe(.05) lr:
oglm y x1 x2 x3 x4 , eq2(x1 x2 x3 x4) flip” wont converge unless I
reduce the model and use fewer predictors.

The gologit2 results do indeed mirror the logit results. I was just
wondering if I could use gologit2 to see what variables would be
problematic.

I am interested in testing an interaction between sex and income in
predicting success on a dichotomous variable. If i model using oglm
without the interaction and ", het(sex)" the lnsigma for sex is
significant. When I include the sexXincome interaction with ",
het(sex)" the lnsigma for sex is no longer significant (or even
close). I interpret this to mean the interaction has in effect dealt
with the hetero problem, correct?

But how can I tell if other predictors in the model that might also be
problematic?

Thanks again--this is really helpful.

On Tue, Oct 25, 2011 at 2:51 PM, Richard Williams
<richardwilliams.ndu@gmail.com> wrote:
> At 12:15 PM 10/25/2011, Rourke O'Brien wrote:
>>
>> Thanks so much for the follow up!
>>
>> Yes the DV is dichotomous. Does the Brant test work for dichotomous
>> variables? I kept getting errors that there had to be multiple levels
>> (ordinal).
>
> The brant test doesn't make any sense with a dichotomous dv; there is
> nothing to test when there are only 2 possible values. Basically there is
> only one line/regression so there are no parallel lines/regressions to look
> at.
>
> For that matter there is no particular reason to use gologit2 with a
> dichotomous dv either, unless maybe you want to take advantage of some of
> the few things it can do that logit can't. If you look at your gologit2
> results you should see they are the same as your logit/ologit results; if
> not let me know.
>
>> If I use gologit2 to identify problematic variables can I also use it
>> to estimate a model that corrects for the hetero (by denoting which
>> vars meet the pl assumption and which do not)? Or do I need to use
>> that information and run the model in oglm?
>
> If the dv is a dichotomy, I don't think gologit2 can help you identify
> problem vars. With a dichotomous dv, any gologit2 messages you get about a
> var not meeting the parallel lines assumption may be deceptive, since there
> is really nothing to test.
>
> -------------------------------------------
> 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
> 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/
>

*
*   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/