The role of astericks on model fit PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Daniel Lee posted on Saturday, September 22, 2012 - 2:18 am
Hello,

I had a question about the application of asterisks when doing a CFA. When I first ran a 1-factor CFA, I did not put any asterisks on the indicators of my latent variable. The model fit was terrible. However, when running the same model the second time, I included asterisks on the indicators in the 1-factor CFA model. The RMSEA became 0.000, the CFI/TLI became 1.000. I found this very strange. I am wondering why this occurs!

Thank you so much!

Dan
 Linda K. Muthen posted on Saturday, September 22, 2012 - 9:32 pm
If you free all of the factor loadings without fixing the factor variances to one, the model is not identified. For further information, please send the output and license number to support@statmodel.com.
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: