MGCFA Warning PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Madison Silverstein posted on Sunday, January 24, 2016 - 5:41 pm
Hello,

I am running a 7-factor model using MLR in MGCFA comparing two groups (random order and standard order) on a 20-item measure. When I run the model, I receive the following warning message:

WARNING: THE LATENT VARIABLE COVARIANCE MATRIX (PSI) IN GROUP RANDOM
IS NOT POSITIVE DEFINITE. THIS COULD INDICATE A NEGATIVE VARIANCE/
RESIDUAL VARIANCE FOR A LATENT VARIABLE, A CORRELATION GREATER OR EQUAL
TO ONE BETWEEN TWO LATENT VARIABLES, OR A LINEAR DEPENDENCY AMONG MORE
THAN TWO LATENT VARIABLES. CHECK THE TECH4 OUTPUT FOR MORE INFORMATION.
PROBLEM INVOLVING VARIABLE EB.

I believe this might be a problem with the random order group because when I run the 7-factor model in the standard order group using CFA, I do not receive the error. However, when I run the 7-factor model in the random order group using CFA, I do receive the error message. Additionally, I checked all models for negative residuals, and there are none.

Your suggestions are much appreciated! Thank you!
 Bengt O. Muthen posted on Sunday, January 24, 2016 - 5:44 pm
Look at TECH4 to see if you have

A CORRELATION GREATER OR EQUAL
TO ONE BETWEEN TWO LATENT VARIABLES, OR A LINEAR DEPENDENCY AMONG MORE
THAN TWO LATENT VARIABLES.
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: