Re: st: question on GLLAMM

[Michael Ingre <Michael.Ingre@ipm.ki.se>]

On 2004-08-18, at 17.04, lm0542 wrote:

> Dear Stata Experts,
> I would like to estimate a model of occupational
> choice of university graduates, taking as endogenous
> each of the following 3 sequential decision nodes:
Dear Matt,

Unfortunately, not many people answers questions on -gllamm-. I try 
too, but not because I'm an expert ... Hopefully though, my small 
contribution will help to make others aware of the amazing potential of 
-gllamm- so that the user community grows to a critical mass, with more 
responses to -gllamm- questions on Statalist.

-gllamm- can fit a variety of choice models e.g. with 
alternative-specific covariates and multilevel structure of the data. 
Some of them are a bit complicated to implement and needs reshaping of 
the data, generation of alternative-dummy variables and the use of the 
-expand()- option.

There is a brief example of a choice model with alternative specific 
covariates in the manual (chapter 9) that can be downloaded here: 
http://www.gllamm.org. Also, there are a few examples in:  
http://stata.com/bookstore/glvm.html (chapter 13) but, the book does 
not discuss how to implement them with -gllamm-. There are however some 
.do files and datasets available for download here 
http://www.gllamm.org/books/genlat.html.

My guess is that the forthcoming book by Sophia Rabe-Hesketh, Andrew 
Pickles, and Anders Skrondal will be the long time needed revision of 
the manual with direct references to -gllamm- 
http://www.stata-press.com/forthcoming.html. You should check it out 
when it is released.


> I was thinking to use GLLAMM for this purpose but
> since I'm new to the program I'm not sure whether it
> might be suitable.
I can't say for sure, but if you have longitudinal/multilevel-data and 
use Stata, then -gllamm- seems to me to be the obvious first choice.

Michael




*
*   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/