On the Overuse and Misuse of Mediation Analysis: It May Be a Matter of Timing

Kenny (2008) credited Hyman (1955 Hyman, H. (1955). Survey design and analysis: Principles, cases and procedures. Glencoe, IL: The Free Press. Google Scholar]) with originally discussing mediation analysis under the name elaboration. Of importance, Hyman's elaboration required a time-ordered relationship among variables, such that the mediator must always intervene in time between the predictor and outcome. However, in the modern discussions of mediation (e.g., Baron & Kenny, 1986 Baron, R., & Kenny, D. A. (1986). The moderator–mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51, 1173–1182. doi:10.1037/0022-3514.51.6.1173Crossref], PubMed], Web of Science ®] , Google Scholar]; Preacher & Hayes, 2004 Preacher, K. J., & Hayes, A. F. (2004). SPSS and SAS procedures for estimating indirect effects in simple mediation models. Behavior Research Methods, Instruments, & Computers, 36, 717–731. doi:10.3758/bf03206553Crossref], PubMed] , Google Scholar]), this crucial point about time-ordered relationships appears to be underemphasized. This article shows that by employing a conceptual timing criterion for all mediation analyses, the overuse of this technique can be curbed, and, simultaneously, researchers will understand when mediation analyses are appropriate across the behavioral and medical science literatures.