A Regularized GLS for Structural Equation Modeling. Issue 5 (3rd September 2017)

• Record Type: Journal Article
• Authors: Arruda, Erin H.; Bentler, Peter M.
• Is Part Of: Structural equation modeling. Volume 24:Issue 5(2017)
• Page Start: 657
• Page End: 665
• Publication Date: 2017-09-03
• Subjects: condition number -- model fit -- regularization -- shrinkage -- weight matrix; Multivariate analysis -- Periodicals; Social sciences -- Statistical methods -- Periodicals; 519.535
• DOI: 10.1080/10705511.2017.1318392
• Languages: English
• ISSNs: 1070-5511

Abstract

Abstract : Ill conditioning of covariance and weight matrices used in structural equation modeling (SEM) is a possible source of inadequate performance of SEM statistics in nonasymptotic samples. A maximum a posteriori (MAP) covariance matrix is proposed for weight matrix regularization in normal theory generalized least squares (GLS) estimation. Maximum likelihood (ML), GLS, and regularized GLS test statistics (RGLS and rGLS) are studied by simulation in a 15-variable, 3-factor model with 15 levels of sample size varying from 60 to 100, 000. A key result showed that in terms of nominal rejection rates, RGLS outperformed ML at all sample sizes below 500, and GLS at most sample sizes below 500. In larger samples, their performance was equivalent. The second regularization methodology (rGLS) performed well asymptotically, but poorly in small samples. Regularization in SEM deserves further study.