EFA question PreviousNext
Mplus Discussion > Exploratory Factor Analysis >
Message/Author
 Liz Woodruff posted on Thursday, May 12, 2011 - 10:37 am
I requested an EFA for 1-6 factors. # of iterations exceeded with 6 factors and the output didn't give me results for a 5 factor EFA but I did get results for a 6 factor EFA and the Chi sqaure was non-significant. Does this mean that the 6 factor EFA is admissible?

Thank you in advance.
 Liz Woodruff posted on Thursday, May 12, 2011 - 10:53 am
Additionally, am I correct in assuming that Model Constraints cannot be used in EFA. For example, if there is negative residual variance, is it not possible to constrain that particular variable?
 Bengt O. Muthen posted on Thursday, May 12, 2011 - 11:10 am
Yes.

You can constrain residual variances in the ESEM context.
 Liz Woodruff posted on Monday, May 23, 2011 - 10:23 am
OK, great. To constrain residual variances in EFA, would I just use a command such as

DATA: FILE IS F:\DissertationData.dat
VARIABLE: NAMES ARE Y1-Y17;
ANALYSIS: TYPE = EFA 1 7;
Y3@0;

OUTPUT: MODINDICES;
 Linda K. Muthen posted on Monday, May 23, 2011 - 10:36 am
You can't constrain parameters in TYPE=EFA. See Examples 5.24-5.27 to see how ESEM is set up.
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: