Error when correlating residuals PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Kate Stringer posted on Monday, March 29, 2010 - 8:57 am
Hello,

I get the following error after I correlate errors of time 4 with time 6 in my LGC model:

WARNING: THE RESIDUAL COVARIANCE MATRIX (THETA) IS NOT POSITIVE DEFINITE.
THIS COULD INDICATE A NEGATIVE VARIANCE/RESIDUAL VARIANCE FOR AN OBSERVED
VARIABLE, A CORRELATION GREATER OR EQUAL TO ONE BETWEEN TWO OBSERVED
VARIABLES, OR A LINEAR DEPENDENCY AMONG MORE THAN TWO OBSERVED VARIABLES.
CHECK THE RESULTS SECTION FOR MORE INFORMATION.
PROBLEM INVOLVING VARIABLE CC6.

The errors are correlated negatively (while the rest are positive) and greater than 1.

What could be causing this?

Thanks!
 Linda K. Muthen posted on Monday, March 29, 2010 - 9:03 am
It sounds like you have a negative residual variance. If you can't see the problem, please send the full output and your license number to support@statmodel.com.
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: