Error -- Can I report estimates? PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 learningmplus posted on Thursday, June 16, 2011 - 9:17 pm
I got the following message:
Can I still report the estimates as valid? Thanks very much.


THE MODEL ESTIMATION TERMINATED NORMALLY

THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES MAY NOT BE TRUSTWORTHY FOR SOME PARAMETERS DUE TO A NON-POSITIVE DEFINITE FIRST ORDER DERIVATIVE PRODUCT MATRIX. THIS MAY BE DUE TO THE STARTING VALUES BUT MAY ALSO BE AN INDICATION OF MODEL NON-IDENTIFICATION. THE CONDITION NUMBER IS -0.129D-15. PROBLEM INVOLVING PARAMETER 19.

THIS IS MORE LIKELY DUE TO HAVING MORE PARAMETERS THAN THE NUMBER OF CLUSTERS MINUS THE NUMBER OF STRATA WITH MORE THAN ONE CLUSTER.
 Linda K. Muthen posted on Thursday, June 16, 2011 - 11:23 pm
The number of clusters minus the number of strata with more than one cluster is the number of independent units in your analysis. You have more parameters than independent units. The impact of this on your results has not been studied. We give this as a warning.
 learningmplus posted on Friday, June 17, 2011 - 7:51 pm
Thank you! This is helpful to know.
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: