|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
Variance accounted for in EFA |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
|
Is it possible to find the "total variance accounted for" when running an EFA with a dichotomous data set? |
|
|
If the rotation is orthogonal, you can sum the squared factor loadings in a column and divide by the number of factor indicators. This will be in a latent response variable metric. Note that the goal of factor analysis is not to explain variance like principal component analysis but to reproduce sample correlations. |
|
Back to top |
|
|