logo
ResearchBunny Logo
PLS-SEM and reflective constructs: A response to recent criticism and a constructive path forward

Business

PLS-SEM and reflective constructs: A response to recent criticism and a constructive path forward

P. Guenther, M. Guenther, et al.

This article confronts the misconceptions surrounding reflective construct measurement in PLS-SEM, arguing that such models accurately represent theoretically grounded constructs. The research, conducted by Peter Guenther, Miriam Guenther, Christian M. Ringle, Ghasem Zaefarian, and Severina Cartwright, emphasizes the value of a multimethod approach in structural equation modeling to leverage diverse strengths instead of fostering competition among methods.

00:00
00:00
Playback language: English
Abstract
This article addresses criticisms of using reflective construct measurement and its associated evaluation criteria in partial least squares structural equation modeling (PLS-SEM). Critics argue that reflective measurement models exclusively correspond to common factor models, a claim deemed inaccurate and misleading. The authors posit that reflective measurement models represent theoretically grounded constructs, and statistical methods approximate these constructs empirically. They highlight that reflective evaluation criteria are not limited to common factor models and don't compromise validity when applied to composite model estimation. The article advocates for a multimethod approach using the complementary strengths of different SEM methods, rather than pitting them against each other.
Publisher
Industrial Marketing Management
Published On
May 19, 2025
Authors
Peter Guenther, Miriam Guenther, Christian M. Ringle, Ghasem Zaefarian, Severina Cartwright
Tags
reflective construct measurement
PLS-SEM
common factor models
composite model estimation
multimethod approach
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny