Identification problem PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Jack Noone posted on Thursday, October 04, 2007 - 6:34 pm
I have 6 observed categorical variables and in CFA they form two factors (3 to a factor - factors are not related) and the model fits well. I want to use these two factors as dependent variables in a SEM model but i am not sure if this is possible. The model is not identified if i test for second order factors and these factors are only just identified if i run the CFA's seperately for each factor. Do i have a problem? It would be nice to have more indicators but sadly that is not possible. I've just started using mplus and SEM so forgive me if this question seems odd.
 Linda K. Muthen posted on Friday, October 05, 2007 - 9:05 am
You can add observed covariates to the model. It will be identified.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: