Latent mean partial invariance interp... PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Mike C Parent posted on Tuesday, September 21, 2010 - 5:35 pm
Hi,
I'm doing some invariance testing with 2 groups. I did a test of latent mean invariance, and fit dropped from the previous invariance tests. Modification indices suggested that I relax three of the equality constraints on the latent means, and I did so. Now in my results these three means (there are nine latent variables total) have different values. Are these values directly interpretable? e.g., if one is .15, does this mean that group is .15 away from the other group's mean on the metric that the latent variable is measured on?
Thanks!
Mike
 Linda K. Muthen posted on Wednesday, September 22, 2010 - 10:59 am
Factor means must be zero in one group. The means for the other groups are deviations from zero.
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: