An Index and Test of Linear Moderated Mediation

Abstract

I describe a test of linear moderated mediation in path analysis based on an interval estimate of the parameter of a function linking the indirect effect to values of a moderator-a parameter that I call the index of moderated mediation. This test can be used for models that integrate moderation and mediation in which the relationship between the indirect effect and the moderator is estimated as linear, including many of the models described by Edwards and Lambert ( 2007 ) and Preacher, Rucker, and Hayes ( 2007 ) as well as extensions of these models to processes involving multiple mediators operating in parallel or in serial. Generalization of the method to latent variable models is straightforward. Three empirical examples describe the computation of the index and the test, and its implementation is illustrated using Mplus and the PROCESS macro for SPSS and SAS.

Role of food preoccupation and current dieting in the associations of parental feeding practices to emotional eating in young adults: A moderated mediation study

“…Confirmation of moderated mediation was based on the index of moderated mediation (Hayes, 2015). Similar to traditional moderation analyses where a significant interaction suggests that the simple slopes are different from each other (Aiken & West, 1991), a significant index of moderated mediation indicates that the moderator is linearly related to the indirect effect and implies that the conditional indirect effects defined by the two different values of the moderator are statistically different.…”

How can personal development lead to increased engagement? The roles of meaningfulness and perceived line manager relations

“…As this would also affect the indirect relationship between perceived opportunities for development and job engagement via meaningfulness (see Figure 1), it is known as a moderated mediation model. Moderated mediation analyses are used to clarify the boundary conditions of the mechanisms by which a predictor influences an outcome through a mediating process (Preacher, Rucker, & Hayes, 2007;Hayes, 2015). It is particularly useful when a mediational process has been evidenced, yet there remains questions regarding when and in what circumstances this occurs, for example does the mediating process differ for men versus women, or between highly demanding versus highly predictable work environments (Muller et al, 2005).…”

“…Table 6 shows the results of these calculations and confirms that the indirect effect is different at high versus low levels of the moderator, thus meeting the forth condition of moderated mediation. Moreover, the moderated mediation index (a quantified value of the strength of association between the indirect effect and the moderator) is significant: Index = .13; bootstrapped confidence interval = .04 to .27 (Hayes, 2015).Further examination of Table 6 reveals that the indirect effect is significant only at high levels of perceived line manager relations. When perceived line manager relations are low then perceived opportunities for development will not translate into higher levels of meaningfulness, which consequently will not lead to greater engagement.…”

“…Table 6 shows the results of these calculations and confirms that the indirect effect is different at high versus low levels of the moderator, thus meeting the forth condition of moderated mediation. Moreover, the moderated mediation index (a quantified value of the strength of association between the indirect effect and the moderator) is significant: Index = .13; bootstrapped confidence interval = .04 to .27 (Hayes, 2015).…”

Are conservative approaches to new product selling a blessing in disguise?

“…To test whether effort, in its relationship with performance, both mediates and interacts with CSB, we calculated the index of moderated mediation for CSB (Hayes 2015). In our Bindependent variable as moderator^model, the indirect effect of CSB on SPO through EFF is the product of the effect of CSB from Eq.…”