Second order factor problem PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 joshua weller posted on Tuesday, October 28, 2008 - 1:41 pm
I am trying to do a CFA with and 2nd order factor, but am getting an error. Here is the syntax that i am using:

Model: f1 BY y1 -y4;
f2 BY y5 -y8;
f3 BY y9-y12;
f4 BY y13-16;
f5 BY y17-20;
f6 BY y21-24;
f7 BY f1 f2 f3;

If I set two of the three factors in f7 to 1, the model runs without error; however, if only one loading in the second-level variable is set to 1, i receive the following message:

WARNING: THE LATENT VARIABLE COVARIANCE MATRIX (PSI) 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 F2.

When I check F2, the b/c the higher order factor's estimated correlation with one of the level-1 factors is greater than zero. Can you help?
 Linda K. Muthen posted on Tuesday, October 28, 2008 - 3:03 pm
If a first- and second-order factor correlate greater than one, you need to change the model.
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: