Items for consideration in a reporting guideline for mediation analyses: a Delphi study.

Objectives: Mediation analysis is a widely used quantitative method for investigating how interventions and exposures in randomised controlled trials and observational studies have an effect on healthcare outcomes. This study aimed to assess the importance of items that should be considered in a consensus meeting aimed at developing a guideline for reporting mediation analyses.
Design: International online Delphi study.
Participants: International experts in the development and application of mediation analysis.
Main Outcome Measures: The Delphi panel were asked to rate the importance of a list of items for inclusion in a guideline for reporting mediation analyses. Thresholds for disagreement and consensus on importance for inclusion were specified a priori. We used the Research ANd Development/University of California Los Angeles appropriateness method to quantitatively assess the importance for inclusion and panel agreement.
Results: Nineteen expert panellists (10 female) from seven countries agreed to participate. All panellists contributed to all three rounds conducted between 10 June 2019 and 6 November 2019. The panel reached consensus on 34 unique reporting items for study design, analytic procedures and effect estimates, with three items rated 'optional'. Panellists added one extra item and provided 60 qualitative comments for item refinement and prioritisation.
Conclusion: This Delphi study used a rigorous consensus process to reach consensus on 34 reporting items for studies that use mediation analysis. These results will inform a consensus meeting that will consolidate a core set of recommended items for reporting mediation analyses.
Competing Interests: Competing interests: AGC is supported by the University of New South Wales Prince of Wales Clinical School Postgraduate Research Scholarship and a NeuRA PhD Candidature Supplementary Scholarship, and is a Catalyst for the Berkeley Initiative for Transparency in the Social Sciences. HL is funded by the National Health and Medical Research Council (APP1126767); National Institute for Health Research (NIHR) Collaboration for Leadership in Applied Health Research and Care Oxford at Oxford Health NHS Foundation Trust; received project funding from the Berkeley Initiative for Transparency in the Social Sciences, a program of the Center for Effective Global Action (CEGA), with support from the Laura and John Arnold Foundation and is a Catalyst for the Berkeley Initiative for Transparency in the Social Sciences. SJK is funded by the National Health and Medical Research Council (APP1127932).
(© Author(s) (or their employer(s)) 2021. No commercial re-use. See rights and permissions. Published by BMJ.)