Steps in MGCFA with continuous variables PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Mary Teresa Granillo posted on Sunday, April 10, 2011 - 8:48 pm
I'm trying to examine the measurement invariance of a scale in 2 populations (White and Latina college students). I have ran the MGCFA with the default settings and that is fine.

However, when I try to free the factor loadings (MODEL: Depress BY Tb1a* Tb1b-Tb1i;)I get an error that says

"THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES COULD NOT BE COMPUTED. THE MODEL MAY NOT BE IDENTIFIED. CHECK YOUR MODEL. PROBLEM INVOLVING PARAMETER 39.
THE CONDITION NUMBER IS -0.744D-06."

Is my syntax incorrect for freeing all parameters?

Thanks,
Teresa
 Mary Teresa Granillo posted on Sunday, April 10, 2011 - 8:50 pm
And I forgot to ask, is this the correct first step in testing for invariance after examining the CFA in each group and in the multiple group CFA?
 Linda K. Muthen posted on Monday, April 11, 2011 - 6:41 am
You are most likely freeing the first factor loading in your group-specific MODEL commands making the model not identified.

The steps for testing for measurement invariance using multiple group analysis are shown in the Topic 1 course handout under Multiple Group Analysis.
 Mary Teresa Granillo posted on Sunday, April 17, 2011 - 5:03 am
Thanks!
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: