Mediation Analyses in Partial Least Squares Structural Equation Modeling, Helping Researchers Discuss More Sophisticated Models: An Abstract

Abstract

Indirect or mediated effects constitute a type of relationship between constructs that often occurs in partial least squares structural equation models (PLS-SEM). Over the past few years, the methods for testing mediation have become more sophisticated. However, many researchers continue to use outdated methods to test mediation effects in PLS-SEM, which can lead to erroneous results. One reason for the use of outdated methods or even ignoring it is that no systematic tutorials on PLS-SEM exist that draw on the newest statistical findings. This study illustrates the state-of-the-art use of mediation analysis in the context of PLS-SEM. It facilitates the adoption of modern procedures in PLS-SEM by challenging the conventional approach to mediation analysis and providing alternatives that are more accurate. In addition, we propose a decision tree and classification of mediation effects. Our recommended approach offers a wide range of testing options that go beyond simple mediation analysis alternatives, helping researchers discuss their studies in a more accurate way.Acknowledgments The authors would like to thank Joseph F. Hair, Christian M. Ringle, and Marko Sarstedt for their fruitful comments and ideas regarding an earlier version of this manuscript.

Potential and Realized Absorptive Capacity as Complementary Drivers of Green Product and Process Innovation Performance

“…A 95% bootstrap confidence interval for the indirect effects is always greater than zero. Hence, the results summarized in Table 4 confirm that structural model has full mediation [69]. Figure 3 summarizes the structural model results.…”

Environmental Proactivity and Firms’ Performance: Mediation Effect of Competitive Advantages in Spanish Wineries

“…This technique has been used previously in similar studies because of its ability to predict one or more dependent variables of a model with a limited theoretical base [75]. Additionally, SEM techniques are particularly recommended for testing the mediation hypothesis [76,77].…”

“…Following Nitzl et al [77], we specify and contract the indirect effects to test our mediation hypothesis (H3). As Table 4 shows, the total effect of the EP on the MPP is much greater than the direct effect and it is also significant (β = 0.332; p < 0.001), which might, according to Sarstedt et al [94], indicate the existence of a mediating effect of the competitive advantages on the relationship between both variables.…”

“…The size of the indirect effect is estimated using the variance accounted for (VAF) index, which in our case is 45.79%, and this indicates that almost half the total MPP effect is explained by the indirect effects of CAD. All things considered, a VAF that is higher than 20% and lower than 80% [73], together with the condition that both the direct and indirect effects are significant [77], suggest that CAD partially mediates in the relationship between the EP and the MPP. However, CAC does not mediate at all in this relationship.…”

Analysis and Evaluation of the Largest 500 Family Firms’ Websites through PLS-SEM Technique

“…An indirect effect is described as a variable that intervenes in the direct relationship between X and Y. The product of the coefficient approach using the bootstrapping resampling method has been used to examine the significance of the indirect effect [78]. The results support the significant mediating role of social network between e-quality and turnover (Tables 5 and 6).…”