Assessing Fit in Structural Equation Models: A Monte-Carlo Evaluation of RMSEA Versus SRMR Confidence Intervals and Tests of Close Fit. Issue 3 (4th May 2018)

• Record Type: Journal Article
• Authors: Maydeu-Olivares, Alberto; Shi, Dexin; Rosseel, Yves
• Is Part Of: Structural equation modeling. Volume 25:Issue 3(2018)
• Page Start: 389
• Page End: 402
• Publication Date: 2018-05-04
• Subjects: goodness-of-fit indexes -- model selection; Multivariate analysis -- Periodicals; Social sciences -- Statistical methods -- Periodicals; 519.535
• DOI: 10.1080/10705511.2017.1389611
• Languages: English
• ISSNs: 1070-5511

Abstract

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.