Problems with rare case model 2 PreviousNext
Mplus Discussion > Categorical Data Modeling >
Message/Author
 Choong-Nam Kang posted on Thursday, May 24, 2007 - 7:05 pm
(cont'd from "problems with rare cases model1)

The error message was:

THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY DUE TO AN ILL-CONDITIONED
FISHER INFORMATION MATRIX. CHANGE YOUR MODEL AND/OR STARTING VALUES.

THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY DUE TO A NON-POSITIVE DEFINITE FISHER INFORMATION MATRIX. THIS MAY BE DUE TO THE STARTING VALUES BUT MAY ALSO BE AN INDICATION OF MODEL NONIDENTIFICATION. THE CONDITION
NUMBER IS 0.367D-23.

THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES COULD NOT BE
COMPUTED. THIS IS OFTEN DUE TO THE STARTING VALUES BUT MAY ALSO BE
AN INDICATION OF MODEL NONIDENTIFICATION. CHANGE YOUR MODEL AND/OR STARTING VALUES. PROBLEM INVOLVING PARAMETER 12.


For your reference, my binary DV has very rare "1" and too many "0"s (52305 cases vs. 2979 cases).

I also tried to change the estimator of the model from MLR to WLSMV. With the WLSMV estimator, the error message was different (NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED).
And I already changed interation number many times (until ITERATIONS=1000000000),
but there was still the same error message.

How to fix this problems?

I really would like to appreciate your advice and any suggestions.

Thank you very much again.
 Linda K. Muthen posted on Thursday, May 24, 2007 - 7:15 pm
Please send your input, data, output, and 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: