Hello Thitima,
You might want to check out -mcl- available at SSC. It uses the
conditional logit model to estimate a multinomial logit model. This
gives you more flexibility, it might be enough for your purposes.
If not, here's an example of how to estimate a multinomial logit
model using -ml-. I've tried several variations, I'm not sure if this
is the most elegant or most efficient. In any case, it might help you
along. The -logan- dataset is available as part of the -mcl- package.
-----------------------------------------------
*et rmsg on
use logan
program define mlr
args lnf eta2 eta3 eta4 eta5
tempvar pi1 pi2 pi3 pi4 pi5
quietly {
gen double
`pi1'=1/(1+exp(`eta2')+exp(`eta3')+exp(`eta4')+exp(`eta5'))
gen double `pi2'=exp(`eta2')*`pi1'
gen double `pi3'=exp(`eta3')*`pi1'
gen double `pi4'=exp(`eta4')*`pi1'
gen double `pi5'=exp(`eta5')*`pi1'
replace `lnf'=($ML_y1==1)*ln(`pi1')+ /*
*/ ($ML_y1==2)*ln(`pi2')+ /*
*/ ($ML_y1==3)*ln(`pi3')+ /*
*/ ($ML_y1==4)*ln(`pi4')+ /*
*/ ($ML_y1==5)*ln(`pi5')
}
end
ml model lf mlr (occ2: educ black) /*
*/ (occ3: educ black) (occ4: educ black) (occ5: occ=educ black)
ml maximize
-----------------------------------------------
Hope this helps,
John Hendrickx
--- PUTTITANUN THITIMA <[email protected]> wrote:
> Dear Statalists,
> I'm trying to find ado file for multinomial logit model so that
> I can
> modify it to fit my research. I know that there is a built-in
> command for
> the multinomial logit model and wondering if anyone has written ado
> file
> for it? Or if anyone know where I can look up so I can try to
> replicate
> the work before I modify it?
>
> Thank you very much in advance,
> Thitima Puttitanun
>
> *
> * 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/
__________________________________________________
Do You Yahoo!?
Yahoo! Finance - Get real-time stock quotes
http://finance.yahoo.com
*
* 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/