Running time for 2-level bifactor model PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 jane  posted on Wednesday, January 29, 2014 - 2:42 pm
Hi,

I am trying to fit a 2-level bifactor model with random intercept and a covariate at the winthin-cluster level.

file=sample list.txt;
type=montecarlo;
usevariables=cluster cov i1-i24;
categorical=i1-i24;
within=cov;
cluster=cluster;

ANALYSIS:
TYPE=TWOLEVEL;

MODEL:
%within%

b1 by i1-i6;
b2 by i7-i12;
b3 by i13-i18;
b4 by i19-i24;
f by i1-i24;
f on cov;
i1-i23 on cov;

b1 with b2 @0;
b1 with b3 @0;
b1 with b4 @0;
b2 with b3 @0;
b2 with b4 @0;
b3 with b4 @0;

I got an error message below:

THERE IS NOT ENOUGH MEMORY SPACE TO RUN Mplus ON THE CURRENT
INPUT FILE. THE ANALYSIS REQUIRES 5 DIMENSIONS OF INTEGRATION RESULTING
IN A TOTAL OF 0.75938E+06 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 OR USE INTEGRATION=MONTECARLO
WITH FEWER NUMBER OF INTEGRATION POINTS SUCH AS 500 OR 5000.

Then I added "INTEGRATION=MONTECARLO", It took about 17 hours to run 100 replications. I am wondering is there a way to speed up the analysis?

Thanks!

Jane
 Bengt O. Muthen posted on Wednesday, January 29, 2014 - 5:37 pm
Use

PROCESSORS = x;

where x is the number of processors your computer has. For this type of work you want at least 8 fast ones.
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: