The Potential for Differential Findings Among Invariance Testing Strategies for Multisample Measured Variable Path Models

Abstract

Multisample measured variable path analysis is used to test whether causal/structural relations among measured variables differ across populations. Several invariance testing approaches are available for assessing cross-group equality of such relations, but the associated test statistics may vary considerably across methods. This study is a population analysis, examining five different strategies for invariance testing using an illustrative measured variable path model. The results demonstrate how inferences about parameters across populations can depend greatly upon the invariance testing approach used, thereby potentially leading to improper inference regarding the true invariance status of relevant parameters.

Keywords

invariance testing multisample path analysis

Get full access to this article

View all access options for this article.

References

Byrne, B.M. (1994). Structural equation modeling with EQS and EQS/Windows: Basic concepts, applications, and programming. Thousand Oaks, CA: Sage.

Chou, C.-P. , & Bentler, P.M. (2002). Model modification in structural equation modeling by imposing constraints. Computational Statistics & Data Analysis, 41, 271-287.

Green, S.B. , Thompson, M.S. , & Babyak, M.A. (1998). A Monte Carlo investigation of methods for controlling type I errors with specification searches in structural equation modeling . Multivariate Behavioral Research, 33, 365-383.

Hutchinson, S.R. (1993). Univariate and multivariate specification search indices in covariance structure modeling. Journal of Experimental Education, 61, 171-181.

Kaplan, D. , & Wenger, R.N. (1993). Asymptotic independence and separability in covariance structure models: Implications for specification error, power, and model modification . Multivariate Behavioral Research, 28, 467-482.

Kline, R.B. (2005). Principles and practice of structural equation modeling (2nd ed.). New York : Guilford.

MacCallum, R. (1986). Specification searches in covariance structure modeling. Psychological Bulletin, 100, 107-120.

MacCallum, R. , Roznowski, M. , & Necowitz, L.B. (1992). Model modifications in covariance structure analysis: The problem of capitalization on chance. Psychological Bulletin, 111, 490-504.

Reichardt, C.S. (2002). The priority of just-identified, recursive models . Psychological Methods, 7, 307-315.

10.

Schoenberg, R. (1972). Strategies for meaningful comparison. Sociological Methodology, 4, 1-35.

11.

Thayer, J.D. (1990). Implementing variable selection techniques in regression. Boston: Annual Meeting of the American Educational Research Association(ERIC Document Reproduction Service No. ED319805).