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 FornellLarcker 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.

Impact of Brand Equity Drivers on Purchase Intention: A Moderating Effect of Entrepreneurial Marketing

“…Moreover, table 5 shows estimation of HTMT ratio for discrimination validity. It has the threshold of less than 0.85, as suggested by Henseler, Ringle, and Sarstedt (2015). HTMT ratio is an advance statistical technique that helps to assess discriminant validity amongst variables in PLS-SEM, as shown in the above table.…”

“…It has clearly shown that all the variables significantly distinct in their domains. The suggested threshold was considered that all the variables have less than 0.85 coefficients in HTMT ratio for achieving adequate discriminant validity (Henseler et al, 2015). Therefore, it has been achieved appropriately for the current study.…”

Impact of Competitive Capabilities on Sustainable Manufacturing Applications in Romanian SMEs from the Textile Industry

“…Table 3 shows that the values of Cronbach's alpha, composite reliability (CR) and rho_A are greater than 0.707 which indicates the acceptable internal reliability of all variables [51]. In addition, the minimum average variance extracted (AVE) value (0.558) surpasses the required cut-off value of 0.5 [52], which reveals an adequate convergent validity level. Additionally, we follow the Fornell and Larcker [53] criterion to assess discriminant validity.…”

Older Adults Use of Online Health Information - Do They Even Try?

“…Discriminant validity was assessed by observing that each item loads highest on its designated construct (i.e., cross-loadings) [57] and by ensuring that the square roots of AVEs are greater than the correlation [58]. The heterotrait-monotrait ratio with highest value of 0.682 is below the threshold of 0.850 and provides further support for sufficient discriminant validity [59].…”