Testing moderating effects in PLS path models with composite variables

Abstract

Purpose

The purpose of this paper is to explain how to model moderating effects of composites using partial least squares (PLS) path modeling. It provides the methodological underpinning of moderating effects in general and describes the various approaches for forming the interaction term, i.e., the product indicator approach, the two-stage approach, and orthogonalization.

Design/methodology/approach

The paper discusses the use of standardized vs unstandardized construct scores and introduces spotlight analysis as a useful way to report findings.

Findings

Researchers should rely on unstandardized estimates when analyzing moderating effects. Centering or orthogonalization can help improve the interpretability of path coefficients.

Practical implications

PLS software implementations should facilitate unstandardized estimates.

Originality/value

This paper formulates step by step guidelines for analyzing moderating effects of composites using PLS path modeling. It is the first to propose spotlight analysis for PLS path modeling.

Citation

Fassott, G., Henseler, J. and Coelho, P.S. (2016), "Testing moderating effects in PLS path models with composite variables", Industrial Management & Data Systems, Vol. 116 No. 9, pp. 1887-1900. https://doi.org/10.1108/IMDS-06-2016-0248

Download as .RIS