search for


Simple power analysis in causal mediation models for a dichotomous outcome based on the mediation proportion
Journal of the Korean Data & Information Science Society 2017;28:669-84
Published online May 31, 2017
© 2017 Korean Data & Information Science Society.

Young Min Kim1 · John Bennett Cologne2 · Harry Michael Cullings3

1Department of Statistics, Kyungpook National University
23Department of Statistics, Radiation E ects Research Foundation
Correspondence to: Young Min Kim
Assistant Professor, Department of Statistics, Kyungpook National University, Daegu 41566, Korea. E-mail:
Received March 16, 2017; Revised May 1, 2017; Accepted May 8, 2017.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Mediation models are widely used in many elds of research and have recently gained attention in epidemiology. The mediation proportion is a standard measure to evaluate what part of the total exposure effect on an outcome may be explained by a particular mediator and to examine how important that pathway is relative to the overall exposure effect. A common question is how large a sample size is needed to achieve high statistical power or, equivalently, what magnitude of effect can be detected. Current power and sample size calculations for mediation analysis are limited and additional research is needed. We therefore propose a computer-intensive power analysis using the mediation proportion. We conduct simulation studies to calculate statistical powers and sample sizes. And then, we illustrate our power analysis using an example from the Adult Health Study of atomic-bomb survivors and demonstrate that the method is relatively straightforward to understand and compute.
Keywords : Bias-corrected bootstrap, dichotomous outcomes, mediation proportion, natural direct and indirect effects, power analysis.

KDISS e-Submission go

May 2017, 28 (3)