What is it about?
This article provides an overview of modern, regression-based causal mediation analysis approach by Valeri & VanderWeele (2013). We revisit the study design considerations, and the definition of direct and indirect effects. We also provide researchers in the field of traumatic stress with an introduction to implementing this causal mediation analysis method using our new R package 'regmedint'. To illustrate how to conduct and interpret mediation analysis using 'regmedint', we use data from a published longitudinal study to assess the extent to which children’s externalizing behavior mediates changes in parental negative feelings during the COVID-19 lockdown.
Photo by vackground.com on Unsplash
Why is it important?
Mediation analysis studies the internal causal mechanism between an exposure and an outcome. The modern causal mediation analysis overcomes the limitations in traditional mediation literature by allowing more flexible model forms and the interaction between exposure and mediator. The original seminal paper by Valeri & VanderWeele (2013) has only SAS, STATA and SPSS macros. To make it more accessible to R users, we provide the 'regmedint' package.
Read the Original
This page is a summary of: A brief primer on conducting regression-based causal mediation analysis., Psychological Trauma Theory Research Practice and Policy, January 2023, American Psychological Association (APA), DOI: 10.1037/tra0001421.
You can read the full text:
The following have contributed to this page