CISE Model and Error Message PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Rachel Roiland posted on Sunday, January 29, 2012 - 1:29 pm
Hello Dr. Muthen,
I am attempting to run a model with a three category dependent variable, a continuous mediating variable, 3 independent variables (each measured twice (Time 1 and Time 2)) and 8 covariates. When I run by styntax, I get this error message.
*** FATAL ERROR
THERE IS NOT ENOUGH MEMORY SPACE TO RUN THE PROGRAM ON THE CURRENT
INPUT FILE. THE ANALYSIS REQUIRES 6 DIMENSIONS OF INTEGRATION RESULTING
IN A TOTAL OF 0.11391E+08 INTEGRATION POINTS. THIS MAY BE THE CAUSE
OF THE MEMORY SHORTAGE. YOU CAN TRY TO REDUCE THE NUMBER OF DIMENSIONS
OF INTEGRATION OR THE NUMBER OF INTEGRATION POINTS.

I'm not sure how to interpret this or what my next step would be to ge the model to run. Any information would be greatly appreciated.
Thank you!
 Bengt O. Muthen posted on Sunday, January 29, 2012 - 4:47 pm
With ML, the combination of categorical observed DVs and latent variables results in computations using numerical integration, which is what the message refers to. Although you don't define a latent variable, you probably have missing data on some of your continuous DVs, implying that these variables are partly latent. You should look at the missing data patterns (PATTERN option of the OUTPUT command) - perhaps you can eliminate some subjects to make one or more variables not have missingness. You can also try integration=montecarlo. Or, you can switch from ML to WLSMV or Bayesian estimation.
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: