A new criterion for assessing discriminant validity in variance-based structural equation modeling

Jörg Henseler, Christian M. Ringle, Marko Sarstedt

Research output: Contribution to journalArticleAcademicpeer-review

2066 Citations (Scopus)
638 Downloads (Pure)

Abstract

Discriminant validity assessment has become a generally accepted prerequisite for analyzing relationships between latent variables. For variance-based structural equation modeling, such as partial least squares, the Fornell-Larcker criterion and the examination of cross-loadings are the dominant approaches for evaluating discriminant validity. By means of a simulation study, we show that these approaches do not reliably detect the lack of discriminant validity in common research situations. We therefore propose an alternative approach, based on the multitrait-multimethod matrix, to assess discriminant validity: the heterotrait-monotrait ratio of correlations. We demonstrate its superior performance by means of a Monte Carlo simulation study, in which we compare the new approach to the Fornell-Larcker criterion and the assessment of (partial) cross-loadings. Finally, we provide guidelines on how to handle discriminant validity issues in variance-based structural equation modeling.
Original languageEnglish
Pages (from-to)115-135
JournalJournal of the Academy of Marketing Science
Volume43
Issue number1
DOIs
Publication statusPublished - 2015

Fingerprint

Discriminant validity
Structural equation modeling
Simulation study
Multi-method
Latent variables
Monte Carlo simulation
Partial least squares

Keywords

  • IR-91561
  • METIS-304728
  • Structural equation modeling (SEM)
  • Partial least squares (PLS)
  • Results evaluation
  • Measurement model assessment
  • Discriminant validity
  • Fornell-Larcker criterion
  • Cross-loadings
  • Multitrait-multimethod (MTMM) matrix
  • Heterotrait-monotrait (HTMT) ratio of correlations

Cite this

@article{8706744597dc4c488325fd0cc242ceeb,
title = "A new criterion for assessing discriminant validity in variance-based structural equation modeling",
abstract = "Discriminant validity assessment has become a generally accepted prerequisite for analyzing relationships between latent variables. For variance-based structural equation modeling, such as partial least squares, the Fornell-Larcker criterion and the examination of cross-loadings are the dominant approaches for evaluating discriminant validity. By means of a simulation study, we show that these approaches do not reliably detect the lack of discriminant validity in common research situations. We therefore propose an alternative approach, based on the multitrait-multimethod matrix, to assess discriminant validity: the heterotrait-monotrait ratio of correlations. We demonstrate its superior performance by means of a Monte Carlo simulation study, in which we compare the new approach to the Fornell-Larcker criterion and the assessment of (partial) cross-loadings. Finally, we provide guidelines on how to handle discriminant validity issues in variance-based structural equation modeling.",
keywords = "IR-91561, METIS-304728, Structural equation modeling (SEM) , Partial least squares (PLS), Results evaluation, Measurement model assessment, Discriminant validity, Fornell-Larcker criterion, Cross-loadings, Multitrait-multimethod (MTMM) matrix, Heterotrait-monotrait (HTMT) ratio of correlations",
author = "J{\"o}rg Henseler and Ringle, {Christian M.} and Marko Sarstedt",
note = "Open access",
year = "2015",
doi = "10.1007/s11747-014-0403-8",
language = "English",
volume = "43",
pages = "115--135",
journal = "Journal of the Academy of Marketing Science",
issn = "0092-0703",
publisher = "Springer",
number = "1",

}

A new criterion for assessing discriminant validity in variance-based structural equation modeling. / Henseler, Jörg; Ringle, Christian M.; Sarstedt, Marko.

In: Journal of the Academy of Marketing Science, Vol. 43, No. 1, 2015, p. 115-135.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A new criterion for assessing discriminant validity in variance-based structural equation modeling

AU - Henseler, Jörg

AU - Ringle, Christian M.

AU - Sarstedt, Marko

N1 - Open access

PY - 2015

Y1 - 2015

N2 - Discriminant validity assessment has become a generally accepted prerequisite for analyzing relationships between latent variables. For variance-based structural equation modeling, such as partial least squares, the Fornell-Larcker criterion and the examination of cross-loadings are the dominant approaches for evaluating discriminant validity. By means of a simulation study, we show that these approaches do not reliably detect the lack of discriminant validity in common research situations. We therefore propose an alternative approach, based on the multitrait-multimethod matrix, to assess discriminant validity: the heterotrait-monotrait ratio of correlations. We demonstrate its superior performance by means of a Monte Carlo simulation study, in which we compare the new approach to the Fornell-Larcker criterion and the assessment of (partial) cross-loadings. Finally, we provide guidelines on how to handle discriminant validity issues in variance-based structural equation modeling.

AB - Discriminant validity assessment has become a generally accepted prerequisite for analyzing relationships between latent variables. For variance-based structural equation modeling, such as partial least squares, the Fornell-Larcker criterion and the examination of cross-loadings are the dominant approaches for evaluating discriminant validity. By means of a simulation study, we show that these approaches do not reliably detect the lack of discriminant validity in common research situations. We therefore propose an alternative approach, based on the multitrait-multimethod matrix, to assess discriminant validity: the heterotrait-monotrait ratio of correlations. We demonstrate its superior performance by means of a Monte Carlo simulation study, in which we compare the new approach to the Fornell-Larcker criterion and the assessment of (partial) cross-loadings. Finally, we provide guidelines on how to handle discriminant validity issues in variance-based structural equation modeling.

KW - IR-91561

KW - METIS-304728

KW - Structural equation modeling (SEM)

KW - Partial least squares (PLS)

KW - Results evaluation

KW - Measurement model assessment

KW - Discriminant validity

KW - Fornell-Larcker criterion

KW - Cross-loadings

KW - Multitrait-multimethod (MTMM) matrix

KW - Heterotrait-monotrait (HTMT) ratio of correlations

U2 - 10.1007/s11747-014-0403-8

DO - 10.1007/s11747-014-0403-8

M3 - Article

VL - 43

SP - 115

EP - 135

JO - Journal of the Academy of Marketing Science

JF - Journal of the Academy of Marketing Science

SN - 0092-0703

IS - 1

ER -