Header

UZH-Logo

Maintenance Infos

Choosing priors in bayesian measurement invariance modeling: A Monte Carlo Simulation study


Pokropek, Artur; Schmidt, Peter; Davidov, Eldad (2020). Choosing priors in bayesian measurement invariance modeling: A Monte Carlo Simulation study. Structural Equation Modeling:Epub ahead of print.

Abstract

Multi-group Bayesian structural equation modeling (MG-BSEM) gained considerable attention among substantive researchers investigating cross-group differences and methodologists exploring challenges in measurement invariance testing. MG-BSEM allows for greater flexibility by applying elastic rather than strict equality constraints on item parameters across groups. This, however, requires a specification of user-defined prior variances for cross-group differences in item parameters. Although prior selection in general Bayesian settings is well-studied, guidelines with respect to tuning the normal prior variances in MG-BSEM approximate measurement invariance (AMI) analysis are still largely missing. In a Monte Carlo simulation study we find that correctly specifying prior variances results in more precise credibility intervals (CI) and posterior standard deviations, while prior misspecification has little influence on point estimates. We compared the BIC, DIC, and PPP fit measures and found in our simulation scenarios that the DIC measure was most effective, when a proper threshold for model selection was applied.

Abstract

Multi-group Bayesian structural equation modeling (MG-BSEM) gained considerable attention among substantive researchers investigating cross-group differences and methodologists exploring challenges in measurement invariance testing. MG-BSEM allows for greater flexibility by applying elastic rather than strict equality constraints on item parameters across groups. This, however, requires a specification of user-defined prior variances for cross-group differences in item parameters. Although prior selection in general Bayesian settings is well-studied, guidelines with respect to tuning the normal prior variances in MG-BSEM approximate measurement invariance (AMI) analysis are still largely missing. In a Monte Carlo simulation study we find that correctly specifying prior variances results in more precise credibility intervals (CI) and posterior standard deviations, while prior misspecification has little influence on point estimates. We compared the BIC, DIC, and PPP fit measures and found in our simulation scenarios that the DIC measure was most effective, when a proper threshold for model selection was applied.

Statistics

Citations

Altmetrics

Downloads

2 downloads since deposited on 24 Jan 2020
2 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Business Administration
06 Faculty of Arts > Institute of Sociology
08 Research Priority Programs > Social Networks
Dewey Decimal Classification:330 Economics
Scopus Subject Areas:Social Sciences & Humanities > General Decision Sciences
Physical Sciences > Modeling and Simulation
Social Sciences & Humanities > Sociology and Political Science
Social Sciences & Humanities > General Economics, Econometrics and Finance
Uncontrolled Keywords:Measurement invariance, Bayesian structural equation modeling (BSEM), cross-group comparisons, Monte Carlo simulation study
Language:English
Date:15 January 2020
Deposited On:24 Jan 2020 10:12
Last Modified:29 Jul 2020 13:40
Publisher:Taylor & Francis
ISSN:1070-5511
Additional Information:This is an Accepted Manuscript of an article published by Taylor & Francis available online: http://wwww.tandfonline.com/10.1080/10705511.2019.1703708
OA Status:Closed
Publisher DOI:https://doi.org/10.1080/10705511.2019.1703708
Other Identification Number:merlin-id:19005

Download

Closed Access: Download allowed only for UZH members

Content: Accepted Version
Language: English
Filetype: PDF - Registered users only until 1 January 2021
Size: 865kB
View at publisher
Embargo till: 2021-01-01