Multilevel and multiple mediation in ... PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Beatriz Sora posted on Monday, July 26, 2010 - 1:26 pm
Hello,

I am trying to develop a multilevel and multiple mediation model (one independent variable at higher level, two mediator variables at lower level and four dependent variables: 2-1-1), but the M-plus software indicates the following error:

THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY DUE TO A NON-ZERO DERIVATIVE OF THE OBSERVED-DATA LOGLIKELIHOOD.

THE MCONVERGENCE CRITERION OF THE EM ALGORITHM IS NOT FULFILLED. CHECK YOUR STARTING VALUES OR INCREASE THE NUMBER OF MITERATIONS. ESTIMATES CANNOT BE TRUSTED. THE LOGLIKELIHOOD DERIVATIVE FOR PARAMETER 52 IS 0.74657505D+00.

I have followed its instructions and I have increased the number of interactions and mconverge, more especifically I have included the following instructions, but it does not work either.
MITERATIONS IS 1000;
MCONVERGENCE IS 0.1;

I would thank any suggestion so that my model can work.
Thank you very much,
Bea
 Linda K. Muthen posted on Monday, July 26, 2010 - 1:39 pm
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: