Negative scaling factor for MLR PreviousNext
Mplus Discussion > Dynamic Structural Equation Modeling >
Message/Author
 Teun Siebers posted on Monday, October 26, 2020 - 6:29 am
Hello,

When I try to compare my Model 1 to Model 2, I get a negative scaling correction for MLR.

I following the procedure for the Strictly Positive
Satorra-Bentler Chi-Square Test. However, I get back an error message.

My model specification:
%WITHIN%
SRG01E1 ON BeepTE1*0.01418;
SRG01E1 ON weekday*-0.10478;
smuEffect | SRG01E1 ON smu;

SRG01E1*1.86359;

%BETWEEN%
SRG01E1 ON smuPM*0.23266;
[ SRG01E1*1.47079 ];
SRG01E1*1.03723;
[ smuEffect*0.11074 ];
smuEffect* 0;

The error:
" THE ESTIMATED BETWEEN COVARIANCE MATRIX IS NOT POSITIVE DEFINITE AS IT
SHOULD BE. COMPUTATION COULD NOT BE COMPLETED.
THE VARIANCE OF SMUEFFEC APPROACHES 0. FIX THIS VARIANCE AND THE
CORRESPONDING COVARIANCES TO 0, DECREASE THE MINIMUM VARIANCE, OR
SPECIFY THE VARIABLE AS A WITHIN VARIABLE.

THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY DUE TO AN ERROR IN THE
COMPUTATION. CHANGE YOUR MODEL AND/OR STARTING VALUES. "

Could you provide suggestions to solve or work around this issue?

Thanks!

Best,
Teun
 Bengt O. Muthen posted on Tuesday, October 27, 2020 - 10:33 am
We need to see your full output to diagnose this - send to Support along with your license number.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a public posting area. Enter your username and password if you have an account. Otherwise, enter your full name as your username and leave the password blank. Your e-mail address is optional.
Password:
E-mail:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: