The Use of Longitudinal Mediation Models for Testing Causal Effects and Measuring Direct and Indirect Effects

Mediation variables are those intervening variables ( M ) that affect the relationship between the independent variable ( X ) and the dependent variable ( Y ). The causal relation between X and Y through the mediation variable M must be established to analyze mediation. M is a mediator, if it involves indirect effects among the set of original variables X and Y . A requirement for a variable to have a causal effect on another is that the cause must precede the outcome in time. This paper argues that the right way to prove the mediation effect is by analyzing different moments in time to support the relations among the variables, which can be done using longitudinal models. The use of traditional analysis in mediation models without the time effect (assumed to occur instantaneously) biases the parameter estimation and could create the possible cancelation of effects, if the paths have opposite signs. Mediation models (without the time effect) are quite frequently used in social sciences. In contrast, the longitudinal mediation model is a very uncommon methodology within the social science community. The aim of this paper is to shed some light about how to analyze the time framework and to provide a methodology to solve the possible limitations that could hinder the robustness of the mediation analysis.