Relative Accuracy of Two Modified Parallel Analysis Methods Using the Proper Reference Distribution

• In Event: Poster Session 2
  In Poster Session: Division D Section 2 Poster Session 1

Abstract

Parallel analysis (PA) assesses the number of factors in exploratory factor analysis. Traditionally PA compares the eigenvalues for a sample correlation matrix with the eigenvalues for correlation matrices for 100 comparison datasets generated such that the variables are independent. This approach uses the wrong reference distribution. The proper reference distribution of eigenvalues assesses the kth factor based on comparison datasets with k–1 underlying factors. Revised PA and comparison data PA use the proper reference distribution and are superior to other approaches based on Monte Carlo studies. We compare the accuracies of these methods using Monte Carlo methods by manipulating the factor structure, factor loadings, factor correlations, and number of observation. The results should affect how parallel analysis is applied.

Authors

• Samuel B. Green, Arizona State University

• Yuning Xu, Arizona State University

• Marilyn S. Thompson, Arizona State University