luke fryer posted on Tuesday, September 07, 2010 - 11:52 pm
Dr. Linda Muthen,
I am a recent convert to the Mplus EFA method. Up until now I have used Parallel analysis and MAP to determine the # of factors. You suggest using fit statistics. My limited use suggests that more factors improves fit (limitlessly). How does one make the cut-off? How are the fit statistics interpreted?
If there is an article that I have missed which explains this please point me in the right direction.
The number of factors that can be extracted is limited by the number of factor indicators. Over factoring leads to negative residual variances and an inadmissible solution. See the Topic 1 course handout and video where determining the number of factors is discussed in detail. See also:
Fabrigar, L.R., Wegener, D.T., MacCallum, R.C. & Strahan, E.J. (1999). Evaluating the use of exploratory factor analysis in psychological research. Psychological Methods, 4, 272-299.