Albert -
Unless you had repeated observations for the same covariate pattern, I
don't see how proportions alone would be enough information to do proper
inference. Those same proportions could have arisen from 100, 1000 or
100000 observations. Clearly the inference would be different for those
situations. If you did have reps, then trying a beta or dirchlet model
fit might work.
Al Feiveson
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Maarten buis
Sent: Friday, March 03, 2006 2:41 PM
To: [email protected]
Subject: Re: st: Multinomial logit in stata
Hi Albert:
This question does occationally come up in the binomial form (choice
between two options), and the answer than is either assuming that the
proportion is beta distributed and use -betafit- with the
-alternitive- option, or use a GLM approach recommended by Papke and
Wooldridge(1996). Now the multivariate equivalent of -betafit- would be
-dirichletfit-, though that program has not been written yet. You might
have more luck trying to extent the approach of Papke and Wooldridge.
HTH,
Maarten
Leslie E. Papke and Jeffrey M. Wooldridge, "Econometric Methods for
Fractional Response Variables with an Application to 401(k) Plan
Participation Rates", Journal of Applied Econometrics, Vol. 11, No. 6,
1996, pp. 619-632.
--- Albert Newton <[email protected]> wrote:
> Does anyone know if stata could do multinomial logit model with
> proportion as dependent variable.
>
> e.g.
>
> choice formprop city Lmkrev Lmkstat Lgrowth Lcable
> 1 0.22 1.00 5.47 36.00 0.03 0.59
> 2 0.11 1.00 5.47 36.00 0.03 0.54
> 3 0.06 1.00 5.47 36.00 0.03 0.59
> 4 0.06 1.00 5.47 36.00 0.03 0.59
> 5 0.56 1.00 5.47 36.00 0.03 0.56
> 1 0.38 2.00 5.48 39.00 0.04 0.59
> 2 0.22 2.00 5.48 39.00 0.04 0.59
> 3 0.11 2.00 5.48 39.00 0.04 0.59
> 4 0.06 2.00 5.48 39.00 0.04 0.59
> 5 0.23 2.00 5.48 39.00 0.04 0.59
-----------------------------------------
between 1/2/2006 and 31/3/2006 I will be visiting the UCLA, during this
time the best way to reach me is by email
Maarten L. Buis
Department of Social Research Methodology Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting adress:
Buitenveldertselaan 3 (Metropolitan), room Z214
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
___________________________________________________________
Yahoo! Messenger - NEW crystal clear PC to PC calling worldwide with
voicemail http://uk.messenger.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/
*
* 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/
