Assessing measure congruence in nomological networks

Evaluations of convergent and discriminant validity are generally conducted by analyzing constructs in isolation or by comparing pairs of latent variables. These approaches ignore the broader nomological network that is intrinsic to a measure’s construct validity, and fail to test the implications o...

Full description

Saved in:
Bibliographic Details
Published in:Journal of business research 2021-06, Vol.130, p.318-334
Main Authors: Franke, George R., Sarstedt, Marko, Danks, Nicholas P.
Format: Article
Language:English
Subjects:
Analysis
Business schools
Congruence
Convergent validity
Discriminant validity
Nomological network
Structural equation modeling
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Evaluations of convergent and discriminant validity are generally conducted by analyzing constructs in isolation or by comparing pairs of latent variables. These approaches ignore the broader nomological network that is intrinsic to a measure’s construct validity, and fail to test the implications of either perfect correlations (convergence) or imperfect correlations (divergence). This paper proposes congruence assessment as a useful approach to simultaneously examining the relationships between multiple latent variables within nomological networks. Two measures are congruent if they have proportionally equal correlations with other constructs. We present measures for quantifying congruence within nomological networks, discuss statistical tests of significance, and demonstrate their performance in simulation studies. We reanalyze three published studies to contrast findings from congruence assessment versus traditional criteria for convergent and discriminant validity. We also discuss methodological and theoretical implications of congruence assessment, and suggest future research directions for both covariance- and composite-based structural equation modeling.
ISSN:0148-2963
1873-7978
DOI:10.1016/j.jbusres.2021.03.003