Jurgita Baltrusaityte wrote:
> For my dissertation, I need to run Hausman tests but
> am not able to do so.
>
> I'm running weighted multinomial logits, and my DV
> (qa2) has three categories. I need to check whether
> category 3 could be combined with category 1.
> Category 2 is the modal category and the base.
>
> These are my commands for one of the models:
>
> . mlogit qa2 qi8 ql1m q331 ushhinc q341 ncgender ncage
> q343 q362 [pw=wtnew2]
>
> .est store all
>
> . mlogit qa2 qi8 ql1m q331 ushhinc q341 ncgender ncage
> q343 q362 [pw=wtnew2] if qa2!=3
>
> . est store partial
>
> . hausman partial all, alleqs constant
> no coefficients in common; specify equation(matchlist)
> for problems with different equation names.
> r(498);
>
> I am not sure what to do next. I checked the on-line
> help for "matchlist" and played around with some
> syntax but didn't get anywhere.
>
> I would very much appreciate your input and will
> welcome any related suggestions.
Well, on my Stata 8.2, I've run the exact same commands on one of my
(electoral) datasets, using a combination of continuous and discrete
explanatory variables (together with a probability weight), and it ran
fine for me.
I have a couple of suggestions:
(1) -update q-, take from it from there, run your commands again and see if
that works
or
(2) run your -mlogit- model with fewer variables and see what happens. If
it works, it may be that excluding the third category of your response
variable renders certain explanatory variables incomparable for
whatever reason.
CLIVE NICHOLAS |t: 0(044)7903 397793
Politics |e: [email protected]
Newcastle University |http://www.ncl.ac.uk/geps
Whereever you go and whatever you do, just remember this. No matter how
many like you, admire you, love you or adore you, the number of people
turning up to your funeral will be largely determined by local weather
conditions.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
