Conducting Monte Carlo simulations with PLS-PM and other variance-based estimators for structural equation models: a tutorial using the R package cSEM
Industrial Management & Data Systems
ISSN: 0263-5577
Article publication date: 18 May 2023
Issue publication date: 29 May 2023
Abstract
Purpose
Structural equation modeling (SEM) is a well-established and frequently applied method in various disciplines. New methods in the context of SEM are being introduced in an ongoing manner. Since formal proof of statistical properties is difficult or impossible, new methods are frequently justified using Monte Carlo simulations. For SEM with covariance-based estimators, several tools are available to perform Monte Carlo simulations. Moreover, several guidelines on how to conduct a Monte Carlo simulation for SEM with these tools have been introduced. In contrast, software to estimate structural equation models with variance-based estimators such as partial least squares path modeling (PLS-PM) is limited.
Design/methodology/approach
As a remedy, the R package cSEM which allows researchers to estimate structural equation models and to perform Monte Carlo simulations for SEM with variance-based estimators has been introduced. This manuscript provides guidelines on how to conduct a Monte Carlo simulation for SEM with variance-based estimators using the R packages cSEM and cSEM.DGP.
Findings
The author introduces and recommends a six-step procedure to be followed in conducting each Monte Carlo simulation.
Originality/value
For each of the steps, common design patterns are given. Moreover, these guidelines are illustrated by an example Monte Carlo simulation with ready-to-use R code showing that PLS-PM needs the constructs to be embedded in a nomological net to yield valuable results.
Keywords
Acknowledgements
An earlier version of this article was published in the following PhD thesis: Schamberger, T. (2022) Methodological Advances in Composite-based Structural Equation Modeling. University of Würzburg/University of Twente, https://doi.org/10.3990/1.9789036553759.
Citation
Schamberger, T. (2023), "Conducting Monte Carlo simulations with PLS-PM and other variance-based estimators for structural equation models: a tutorial using the R package cSEM", Industrial Management & Data Systems, Vol. 123 No. 6, pp. 1789-1813. https://doi.org/10.1108/IMDS-07-2022-0418
Publisher
:Emerald Publishing Limited
Copyright © 2023, Emerald Publishing Limited