Model fit indices PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Nicole Stanoff posted on Tuesday, May 19, 2009 - 11:09 pm
I've been running SEM models that have strange model fit indices.

CFI=.701
TLI=.688
RMSEA=.042

Does anyone know what it means when the RMSEA fit is acceptable, but the CFI and TLI values are poor?
 Bengt O. Muthen posted on Wednesday, May 20, 2009 - 1:30 am
I don't think there is any general guidance on this. One possible explanation is that the variables have low correlations so that the baseline model of CFI (uncorrelated variables) doesn't fit too poorly and therefore the H0 model doesn't fit that much better. Low RMSEA and low chi-square also goes with low correlations.
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: