Differences EFA MPlus versus R PreviousNext
Mplus Discussion > Exploratory Factor Analysis >
Message/Author
 Sophie van der Sluis posted on Friday, April 12, 2019 - 1:12 am
Hi,
I'm running EFA analyses in Mplus as well as R. Using exactly the same input correlation matrix, ML estimation, and GEOMIN rotation (GEOMINQ in R, allowing orthogonal solution), and either or not Kaiser normalization, I get a different EFA solution. Do you maybe have an idea what causes this? I assume its a difference in default settings but I cant seem to find what it is.
 Tihomir Asparouhov posted on Friday, April 12, 2019 - 2:26 pm
The Geomin rotation depends on a small epsilon value. This is from the Mplus manual

"The GEOMIN epsilon (Browne, 2001) default setting varies as a function of the number of factors. With two factors, it is .0001. With three factors, it is .001. With four or more factors, it is .01. The default can be overridden using the GEOMIN option."

So probably that is the difference.
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: