Skip Navigation
Skip to contents

JPMPH : Journal of Preventive Medicine and Public Health

OPEN ACCESS
SEARCH
Search

Author index

Page Path
HOME > Browse Articles > Author index
Search
Sangmin Byeon 1 Article
An Introduction to Causal Mediation Analysis With a Comparison of 2 R Packages
Sangmin Byeon, Woojoo Lee
J Prev Med Public Health. 2023;56(4):303-311.   Published online July 31, 2023
DOI: https://doi.org/10.3961/jpmph.23.189
  • 3,692 View
  • 245 Download
AbstractAbstract AbstractSummary PDFSupplementary Material
Traditional mediation analysis, which relies on linear regression models, has faced criticism due to its limited suitability for cases involving different types of variables and complex covariates, such as interactions. This can result in unclear definitions of direct and indirect effects. As an alternative, causal mediation analysis using the counterfactual framework has been introduced to provide clearer definitions of direct and indirect effects while allowing for more flexible modeling methods. However, the conceptual understanding of this approach based on the counterfactual framework remains challenging for applied researchers. To address this issue, the present article was written to highlight and illustrate the definitions of causal estimands, including controlled direct effect, natural direct effect, and natural indirect effect, based on the key concept of nested counterfactuals. Furthermore, we recommend using 2 R packages, ‘medflex’ and ‘mediation’, to perform causal mediation analysis and provide public health examples. The article also offers caveats and guidelines for accurate interpretation of the results.
Summary
Korean summary
전통적 매개분석은 여러 유형의 변수 혹은 복잡한 상호작용을 포함할 경우, 직접 및 간접효과의 정의가 불분명하다는 비판에 직면해왔다. 이에 대한 대안으로서 인과매개분석은 반사실적 개념에 기반하여 직접 및 간접효과를 명료하게 정의하며 유연한 모델링을 가능하게 한다. 다만 이 새로운 접근의 주요 개념을 응용 연구자들이 이해하는 데에는 다소 어려운 측면이 있다. 이러한 점에서 이 논문에서는 중첩된 반사실적 변수에 기반한 인과적 모수의 정의를 상술하고 인과매개분석을 위한 대표적인 R 패키지인 medflex 및 mediation을 활용하여 공공 보건 사례에 대한 분석 실례 및 유의사항을 제공하였다.

JPMPH : Journal of Preventive Medicine and Public Health