At 03:48 PM 1/6/2004 -0500, you wrote:
>Hi,
>
>I am trying to estimate the following latent variable model and I would
>like to know how to do it in Stata:
>
>Y = AZ + e
>Z = BX + u
>
>where Z is an individual unobserved/latent variable, Y is a vector of
>variables (potential indicators of Z), X is another vector of variables
>(potential causes of Z), and u and e are typical errors.
>
>This is the standard form of the Multiple Indicator- Multiple Cause
>model (MIMIC), but I do not know how should be estimated in stata. My
>goal is to have a relieable estimation of B in order to use it to
>calculate the latent variable Z
>
>thanks in advance for your help
>
>Facundo Martin
>Department of Economics
>University of Maryland
Latent variable models, including MIMIC models, can be estimated using a
free Stata add-on known as GLLAMM, for Generalized Linear Latent and Mixed
Models. See <http://www.gllamm.org/>.
Regards,
Dale W. Larson
Larson Global Consulting, Inc. | Potomac Associates*
2824 Greenvale Street
Chevy Chase, MD 20815
Tel: (301) 613-1881
E-mail: <[email protected]>
*International Trade and Economic Development
www.PotomacAssocs.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/
