Second-order EFA with dichotomous var... PreviousNext
Mplus Discussion > Exploratory Factor Analysis >
Message/Author
 Hervé CACI posted on Friday, May 17, 2002 - 1:22 am
Hello,

How can I run a second-order EFA when all my variables are dichotomous ?

Can I simply run a second EFA with the correlation matrix printed out at the first stage ? In that case, does it matter using the WLSMV estimator again ?

Thanks in advance.
 bmuthen posted on Friday, May 17, 2002 - 7:49 am
You can run a second EFA using the estimated correlation matrix as you say. This would have two drawbacks, however. First, you can only use the ULS estimator since you don't then have the raw data to compute the weight matrix of WLSMV. Second, the estimated correlation matrix does not have the second-order structure imposed on it. You can instead do an "EFA within a CFA framework" and do the second-order modeling directly. You may also want to consult the old psychometric literature on "Schmid-Leiman orthogonalization".
 Hervé CACI posted on Friday, September 06, 2002 - 7:24 am
Where can I find a description for doing an "EFA with a CFA framework" and the "Schmid-Leiman orthogonalization" ?
 Linda K. Muthen posted on Friday, September 06, 2002 - 10:13 am
Following is the Schmid-Leiman reference:

Schmid, J. & Leiman, J.M. (1957). The development of hierarchical factor solutions. Psychometrika, 22, 53-61.

Following is the EFA in a CFA framework reference:

Joreskog, K.G. (1969). A general approach to confirmatory maximum likelihood factor analysis.
Psychometrika, 34.
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: