Learning Outcomes

1. Understand the basic concepts of mediation in a PLS-SEM context.
2. Execute a mediation analysis using SmartPLS.
3. Comprehend the basic concepts of moderation in a PLS-SEM context.
4. Use the SmartPLS software to run a moderation analysis.
5. Get to know the principles of a moderated mediation.

Chapter Preview

Structural model relationships in PLS-SEM imply that exogenous constructs directly affect endogenous constructs without any systematic influences of other variables. In many instances, however, this assumption does not hold. Specifically, a third variable in the analysis can change our understanding of the nature of the direct relationships under consideration. The two most prominent examples of such extensions include mediation and moderation.

Mediation occurs when a mediator construct intervenes between two other directly related constructs. More precisely, a change in the exogenous construct results in a change of the mediator construct, which, in turn, changes the endogenous construct. Analyzing the strength of the mediator construct’s relationships with the other constructs enables researchers to substantiate the mechanisms that underlie the cause–effect relationship between an exogenous construct and an endogenous construct. In the simplest form, the analysis considers only one mediator construct, but the path model can also include several mediator constructs.

The other example of a third variable potentially changing a direct relationship in a structural model is moderation. When moderation is present, the strength or even the direction of a relationship between two constructs depends on a third variable (i.e., the moderator). In other words, the relationship between two constructs changes depending on the value of the moderator variable. As an example, the direct relationship between the customer satisfaction and customer loyalty constructs is not the same for all customers but differs depending on moderators such as income, age, and switching costs. For example, the strength of the relationship between customer satisfaction and customer loyalty may be substantially stronger for older customers than for younger customers. Therefore, moderation can (and should) be seen as a means to better understand and account for heterogeneity in the data.

Mediation and moderation are similar in that they describe situations in which the relationship between two constructs depends on a third variable. There are fundamental differences, however, in terms of their theoretical foundation, modeling, and interpretation. In this chapter, we explain and differentiate between mediation and moderation, as well as illustrate their implementation using the corporate reputation PLS path model.