[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

SV: st: GLAMM and nested logit/probit

From   "Kristian Karlson" <>
To   <>
Subject   SV: st: GLAMM and nested logit/probit
Date   Wed, 26 Nov 2008 17:11:01 +0100

Dear Stata users

I would like to hear if anyone can help me with my original question in this
thread (see above). I have to model two multinomial logit models
incorporating unobserved heterogeneity. I would like to use -gllamm-. But
maybe another solution is better. Maarten was very helpful in sharpening my
question earlier in this thread; however, he was not able to help me with
this particular model estimation in -gllamm-.

The parts of the model are (to recapitulate the beginning of this thread):
The first choice stands between three educational tracks after primary
school. Contingent on choosing one of these tracks (secondary), the second
choice is between four post-secondary tracks.

A similar model is found in Breen & Jonsson 2000: "Analyzing Educational
Careers: A Multinomial Transition Model", American Sociological Review, vol.
65 no. 5.

I hope that somebody out there is able to help me.

All the best

-----Oprindelig meddelelse-----
[] På vegne af Maarten buis
Sendt: 18. november 2008 23:57
Emne: RE: st: GLAMM and nested logit/probit

--- Kristian Karlson <> wrote:
> I have, however, not found a presentation of how to model a nested
> multinomial logit model, hence this thread on the statalist.

This is a very specific model, so I it may well be that you are the
first to try that with -gllamm-.
> (For clarification: Yes, you get it right ? the idea was to model the
> latent class membership. How specifically to do this I haven't
> decided on yet.

That reminds me of the work done by Partha Deb who parameterized the
probability of class membership in a finite mixture model. He wrote his
own Stata program though and did not use -gllamm-, but the slides from
his presentation at the Summer North American Stata Users' Meeting may
give you some ideas:

> Nonetheless, my problem here is technical. Maybe I need to go through
> the gllamm manual once again (and this time read it more in depth).
> However, if anyone can give me a helping hand with the estimation of
> the nested multinomial logit model in -gllamm- stated in the top of
> this thread, I would be thankful.

I have never estimated such a model in -gllamm-, so I am afraid I can't
help with that. 

-- Maarten

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515

+31 20 5986715

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index