Rotation to a Partially Specified Target Matrix in Exploratory Factor Analysis in Practice

• In Event: Factor Analysis: Model Specification and Fit

Abstract

The purpose was to explore the influence of the number of targets specified on the quality of exploratory factor analysis solutions with a complex underlying structure and incomplete measurement theory. A Monte Carlo study manipulated target error, number of targets, model error, overdetermination, communality, and sample size. Outcomes included a measure of congruence and a measure of variability with regard to the rotated pattern matrix. Consistent with theoretical expectations, small to moderate effects were observed for the number of targets, while the effects of target error were negligible. Further, target rotation generally performed at least as well as geomin rotation did, which underscores the potential importance of using extant measurement theory to inform the rotation criterion in a non-mechanical way.

Authors

• Nicholas D. Myers, University of Miami

• Ying Jin, University of Miami

• Soyeon Ahn, University of Miami