Fit Indices in Exploratory Factor Analysis for Ordered Categorical Data

• In Event: Roundtable Session 117
  In Roundtable Session: Issues in Model Specification and Fit in Factor Analysis

Abstract

Asparouhov and Muthén (2009) proposed exploratory structural equation modeling (ESEM). Such a framework allows for specification of exploratory factor analysis (EFA) model as a measurement component of a larger SEM model and use of chi-square test and a variety of fit indices developed based on SEM. In EFA model, competing models often differ in the number of factors which tends to involve a larger number of model parameters than confirmatory factor analysis (CFA), therefore the cutoffs established from the CFA framework might not be suitable for EFA. This study examined the performance of commonly reported fit indices in EFA models with computer simulated data for ordered categorical data.

Authors

• Yanyun Yang, Florida State University

• Yan Xia, Florida State University