Residual correlation of 1.000 PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
 Rebecca Fraser posted on Wednesday, December 03, 2008 - 7:24 am

I am running a model as follows:
Type is Twolevel;
y1 on x1 x2
y2 on x3 x4 x5

In running my model, I have received the following message:
The estimated between covariance matrix is not positive definite as it should be. Computation could not be completed. Problem involving variable y1. The residual correlation between y1 and y2 is 1.000.

How can I deal with this issue? Any suggestion would be much appreciated.

Many thanks,
 Linda K. Muthen posted on Wednesday, December 03, 2008 - 8:38 am
If you are not using the most recent version of Mplus, that would be my first suggestion. Then do a TYPE=TWOLEVEL BASIC to see the between-level correlation between these two variables.
 Rebecca Fraser posted on Friday, January 09, 2009 - 3:21 pm
Thanks so much Linda. Utilizing the most recent version solved the problem.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message