Variance in scores accounted for by m... PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 Joseph E. Glass posted on Wednesday, January 18, 2012 - 11:19 am
I have been asked by a reviewer to report the "proportion of the variance in scores accounted for by the CFA model". I assume that he or she is asking for the proportion of variance that is explained in the observed measures, which I understand is typically the item R^2. I have a CFA model with 12 categorical indicators, analyzed with WLSMV. There is one substantive factor (all 12 items) and one method factor (6 of the 12 items).

I would report the item R^2 values, however, I understand that the R-square for each indicator listed in the output is actually the proportion of variance in the latent response variable (for each item) that is explained by the latent factor. Is there a standard for reporting "proportion of variance explained" when using WLSMV with categorical indicators?
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: