Problems of Standardization Identification Method in Testing Measurement Invariance Through a Multigroup Confirmatory Factor Analysis

• In Event: Modeling Frameworks for Measurement Issues

Abstract

The standardization identification method (SIM) should not be used in testing measurement invariance through a multigroup confirmatory factor analysis (MCFA). However, the SIM can be encountered frequently in contemporary research. The purpose of the study is to demonstrate the problems of the SIM through mathematical illustrations and two empirical and two generated data examples. Results showed that the SIM resulted in inaccurate factor loading and intercept estimates when factor variances and factor means are not equivalent between groups, respectively. In addition, the SIM detect the level of invariance inconsistently with the reference-variable identification method by increasing chi-square statistics significantly. This paper concludes with the implications and limitations of the study as well as the directions for future studies.

Authors

• Eunju Jung, Texas A&M University

• Myeongsun Yoon, Texas A&M University