Re: st: GLLAMM: how fast for models with latent variables?

[Jean-Fran�ois Godin<jean-francois.godin@umontreal.ca>]

Title: Re: st: GLLAMM: how fast for models with latent variables?

The answer is no, you’re not doing anything wrong!

Why? Because GLLAMM is special ado-file sub-routine that is not implemented in STATA. So STATA has to “ask”  the sub-routine what it has to do!

“The program simply uses Stata's ml commands with method deriv0 to maximise the likelihood which is evaluated by numerical integration. “

See http://www.stata.com/support/meeting/5uk/gllamm.html

I read somewhere that STATA will eventualy include gllamm as a command in STATA! So no more sub-routine program ado-file. For now we need to be patient  (or upgrade our processor)! :)

I’m using the gllamm command on a server, and in my case, it takes about 6 weeks to compute!

Jf



Le 20/10/03 03:50, «?Philippe Huber?» <philippe_huber@freesurf.ch> a écrit?:

> Hello all,
> 
> I am just new here. I started using Stata this week because I want to
> estimate models with latent variables. I'm trying to use gllamm and I am
> a little bit confused.
> 
> My model is rather simple: there are 10 manifest variables (5 normal and
> 5 binomial), 2 latent variables (or factors) and no covariates. I
> experienced that the latent variables have free variance and the first
> loading for each is set to 1. Is it possible to free these loadings and
> set the factors variances to 1?
> 
> Secondly, I used 8 adaptive quadrature points and my sample is only 60
> observations big. Is it normal that Stata needs about 25 minutes to find
> a result (I have a 1900MHz CPU)? Am I doing something wrong?
> 
> I thank you for you help.
> 
> Sincerely
> 
> Philippe Huber
> Department of Econometrics
> University of Geneva
> Switzerland
> 
>