CFA with non-normal continuous data PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Yung Soo Lee posted on Saturday, March 21, 2009 - 2:22 pm
Hi,

I'm trying to run a CFA model with non-normal continuous indicators. I think MLM or MLMV is usually recommended, but I'm wondering if it's OK to use WLSMV in this case.

Also, if I have a mix of non-normal continuous and ordinal indicators, WLSMV might be a good choice, right?

Thank you.
 Bengt O. Muthen posted on Saturday, March 21, 2009 - 2:50 pm
Both MLR and WLSMV are good choices. When there are categorical outcomes and many factors, ML (MLR) is computationally heavy due to numerical integration being required.
 NR posted on Monday, March 23, 2009 - 6:40 pm
Hi, Dr. Muthen

Is there any reference on the performance of WLSMV for (non-normal) CONTINUOUS data?
 Bengt O. Muthen posted on Monday, March 23, 2009 - 7:02 pm
Not that I am aware of.
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: