Type of CFA - fscores output PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Wouter Steenbeek posted on Thursday, September 24, 2009 - 2:27 am
I did a simple CFA, y BY x1-x8, and outputted the scores. Those factor scores have a standard deviation of ca 0.5 (or a bit higher).
SPSS gives me factor scores with an s.d. of 1 or almost 1; it only differs slightly between principal components, axis factoring, and using maximum likelihood. I tried to save scores as regression, bartlett, Anderson-Rubin, but all give similar results.

So now I'm not sure how to interpret the Mplus results. What kind of (CFA) factor analysis is performed by default, exactly? And with what method are the scores saved?
 Linda K. Muthen posted on Thursday, September 24, 2009 - 10:54 am
With maximum likelihood and continuous outcomes, Mplus uses the regression method to compute factor scores. It is known in the factor score literature that the standard deviation of the factor scores is not the same as the standard deviation of the factor. It may be that SPSS does a standardization after factor score estimation.
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: