Dear Claudio,
thanks for the reply. The problem, I think, is that the Small-Hsiao
statistic use likelihood and with survey data I have
pseudo-likelihood.
I saw the mlogtest code and to get the coefs to do the statistic test
it uses mlogit instead svy:mlogit. I have pweights and then, the coefs
are different using mlogit and svy:mlogit.
Isn't this?
Thanks again!
Joao Lima
2008/10/1 Claudio Cruz Cazares <[email protected]>:
> Hi, try the Small-Hsiao Test.
>
> First you have to set a random value:
>
> . set seed 12345
>
> then,
>
> . mlogtest, smhsiao base
>
> You can try different random values until get the IIA assumption.
>
> Greetings,
>
> Claudio
>
>
>
> ----- Mensaje original -----
> De: "Joao Ricardo F. Lima" <[email protected]>
> Fecha: Martes, Septiembre 30, 2008 10:40 pm
> Asunto: st: IIA test after svy:mlogit
>
>> Dear Stephen and Statalisters,
>>
>> Can I do the Hausman's test for independence of irrelevant
>> alternatives after svy:mlogit? My dependent variable has 4
>> alternatives.
>> I�m using Stata 10.1.
>>
>> I tried to use the -mlogtest-
>>
>> STB-58 sg155 . . . . . . . . . . . . . Tests for the multinomial
>> logit model
>> (help mlogtest, _perhs, _pecats if installed) . J. Freese
>> & J. S. Long
>> 11/00 pp.19--25; STB Reprints Vol 10, pp.247--255
>> simplifies the obtaining of several tests associated with
>> the multinomial logit model
>>
>> However, you can see below that I can�t use with survey data.
>>
>> . mlogtest, hausman base
>>
>> Problem determining number of categories.
>>
>> **** Hausman tests of IIA assumption
>>
>> Ho: Odds(Outcome-J vs Outcome-K) are independent of other
>> alternatives.hausman cannot be used with clustered or p-weighted data
>> r(198);
>>
>> end of do-file
>>
>> r(198);
>>
>> Thanks for the help!
>>
>> Best Regards,
>>
>> Joao Lima
>>
>> *
>> * 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/
>
--
-------------------------------
Joao Ricardo Lima
Professor
UFPB-CCA-DCFS
+553138923914
-------------------------------
*
* 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/
