EFA taking a long time PreviousNext
Mplus Discussion > Exploratory Factor Analysis >
Message/Author
 Mike C Parent posted on Saturday, April 21, 2012 - 3:46 pm
Hi,
I'm running an EFA with a fairly large matrix (about n=250, k=100). There's some missing data, though not an enormous amount, distributed throughout. The analysis is taking a VERY long time to run (I let it sit for 2 hours and it didn't complete).

The actual analysis is simply:

(variables and usevariables omitted for space)

ANALYSIS:
Analysis: type = EFA 1 20;
Rotation = promax;
ESTIMATOR IS ML;
ITERATIONS = 1000;

Might there be an error somewhere I'm not seeing that is messing up the analysis? I am running on a mac using parallels but I've done other complex analyses in mplus that have not taken anywhere near so long (though, I've never done an EFA in mplus before).

Thanks!
 Linda K. Muthen posted on Sunday, April 22, 2012 - 2:09 pm
The number of parameters in the model should not exceed the sample size. I think this is what is causing the slowness. You are asking to extract from one to twenty factors. With twenty factors and l00 variables, the number of free parameters in an EFA model is 1,910. You should try less factors.
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: