Assessing Fit in Structural Equation Models: A Monte-Carlo Evaluation of RMSEA Versus SRMR Confidence Intervals and Tests of Close Fit

Abstract

We compare the accuracy of confidence intervals (CIs) and tests of close fit based on the root mean square error of approximation (RMSEA) with those based on the standardized root mean square residual (SRMR). Investigations used normal and nonnormal data with models ranging from p = 10 to 60 observed variables. CIs and tests of close fit based on the SRMR are generally accurate across all conditions (even at p = 60 with nonnormal data). In contrast, CIs and tests of close fit based on the RMSEA are only accurate in small models. In larger models (p ≥ 30), they incorrectly suggest that models do not fit closely, particularly if sample size is less than 500.

Keywords:

• goodness-of-fit indexes
• model selection

ACKNOWLEDGMENTS

The authors acknowledge the Research Computing Center at the University of South Carolina and the High Performance Computing Center at Weifang University for providing the computing resources used to obtain the results reported in this article.

FUNDING

This research was supported by the National Science Foundation under Grant No. SES-1659936.

Supplemental Material

Supplemental data for this article can be accessed at http://www.tandfonline.com/HSEM