Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Tucker, Graeme (Health)" <Graeme.Tucker@health.sa.gov.au> |
To | "'statalist@hsphsun2.harvard.edu'" <statalist@hsphsun2.harvard.edu> |
Subject | st: FW: SEM |
Date | Wed, 3 Oct 2012 13:33:08 +0930 |
I have used Stata 12 to fit an exploratory factor analysis with an orthogonal rotation. There are 8 manifest variables and two latent variables. The model has a path from each latent variable to every manifest variable, with three constraints on the model. One path from each latent variable has been set to unity, and the correlation between the latent variables is set to zero. Stata fits the model and provides the outputs I need. My problem is that the model should be unidentified. It certainly is in AMOS and LISREL. How does Stata get around this problem? It produces estimates that in my case make perfect sense, and with the expected degrees of freedom. Graeme Tucker Tel: 08 8226 6358 Email: graeme.tucker@health.sa.gov.au * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/