Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


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

st: dynamic structural equations modelling with latent variables


From   "eugenio zucchelli" <eugenio.zucchelli@york.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: dynamic structural equations modelling with latent variables
Date   Wed, 13 Apr 2011 16:32:01 +0100

Dear Statalisters,

I would like to know if it is possible to estimate a dynamic structural
equations model with latent variables using STATA. 

Our model comprises two dynamic structural equations, two latent variables
and a series of measurement equations (essentially it is a MIMIC model with
two dynamic structural equations and two latent variables). 

The model has the following synthetic form:

(1) H*it = H*it-1 + H*it-2 + A*it-1 + A*it-2 + Xit + eit

(2) A*it = A*it-1 + A*it-2 + H*it-1 + H*it-2 + Zit + vit

(3) Hit = H*it + uit

(4) Ait = A*it + wit

where H*it and A*it are two latent variables. 

Note that we need to somehow model the lagged values of the two latent
variables (H*it-1, H*it-2, A*it-1 and A*it-2). Also note that all observed
indicators for our latent constructs (Ait, Hit) are categorical variables
(binary as well as ordinal measures).         

Would you recommend to try to estimate such a model using GLLAMM? If it is
so, is there any way to get around modelling lags of latent variables using
GLLAMM? 

Or would you rather recommend to use a different dedicated software and if
that is the case, which software would you use? (I looked into MPlus and did
not find much about dynamic structural equations models). Besides, I would
like to stick to STATA if possible.  

I am also trying to understand if dynamic factor modelling with latent
variables might be an alternative way to go (as many of you might already
know, STATA has a "dfactor" command for dynamic factor models).    

Any suggestions/comments would be much appreciated!

Thanks a lot.

Best wishes,
Eugenio





**********************************
Eugenio Zucchelli, PhD
Research Fellow
Centre for Health Economics
Alcuin 'A' Block
University of York
Heslington
YORK,  YO10 5DD
UK
**********************************





*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index