Louisa H Smith1, Tyler J VanderWeele1,2. 1. From the Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA. 2. Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA.
Abstract
BACKGROUND: Mediation analysis is a powerful tool for understanding mechanisms, but conclusions about direct and indirect effects will be invalid if there is unmeasured confounding of the mediator-outcome relationship. Sensitivity analysis methods allow researchers to assess the extent of this bias but are not always used. One particularly straightforward technique that requires minimal assumptions is nonetheless difficult to interpret, and so would benefit from a more intuitive parameterization. METHODS: We conducted an exhaustive numerical search over simulated mediation effects, calculating the proportion of scenarios in which a bound for unmeasured mediator-outcome confounding held under an alternative parameterization. RESULTS: In over 99% of cases, the bound for the bias held when we described the strength of confounding directly via the confounder-mediator relationship instead of via the conditional exposure-confounder relationship. CONCLUSIONS: Researchers can conduct sensitivity analysis using a method that describes the strength of the confounder-outcome relationship and the approximate strength of the confounder-mediator relationship that, together, would be required to explain away a direct or indirect effect.
BACKGROUND: Mediation analysis is a powerful tool for understanding mechanisms, but conclusions about direct and indirect effects will be invalid if there is unmeasured confounding of the mediator-outcome relationship. Sensitivity analysis methods allow researchers to assess the extent of this bias but are not always used. One particularly straightforward technique that requires minimal assumptions is nonetheless difficult to interpret, and so would benefit from a more intuitive parameterization. METHODS: We conducted an exhaustive numerical search over simulated mediation effects, calculating the proportion of scenarios in which a bound for unmeasured mediator-outcome confounding held under an alternative parameterization. RESULTS: In over 99% of cases, the bound for the bias held when we described the strength of confounding directly via the confounder-mediator relationship instead of via the conditional exposure-confounder relationship. CONCLUSIONS: Researchers can conduct sensitivity analysis using a method that describes the strength of the confounder-outcome relationship and the approximate strength of the confounder-mediator relationship that, together, would be required to explain away a direct or indirect effect.
Authors: Karly A Murphy; John W Jackson; Tanjala S Purnell; Ashton A Shaffer; Christine E Haugen; Nadia M Chu; Deidra C Crews; Silas P Norman; Dorry L Segev; Mara A McAdams-DeMarco Journal: Clin J Am Soc Nephrol Date: 2020-05-07 Impact factor: 8.237
Authors: Anna M Modest; Louisa H Smith; Thomas L Toth; Ai-Ris Y Collier; Michele R Hacker Journal: Paediatr Perinat Epidemiol Date: 2022-01-04 Impact factor: 3.980
Authors: Hopin Lee; Aidan G Cashin; Sarah E Lamb; Sally Hopewell; Stijn Vansteelandt; Tyler J VanderWeele; David P MacKinnon; Gemma Mansell; Gary S Collins; Robert M Golub; James H McAuley; A Russell Localio; Ludo van Amelsvoort; Eliseo Guallar; Judith Rijnhart; Kimberley Goldsmith; Amanda J Fairchild; Cara C Lewis; Steven J Kamper; Christopher M Williams; Nicholas Henschke Journal: JAMA Date: 2021-09-21 Impact factor: 56.272
Authors: Aidan G Cashin; Hopin Lee; Matthew K Bagg; Benedict M Wand; Edel O'Hagan; Rodrigo R N Rizzo; Tasha R Stanton; G Lorimer Moseley; James H McAuley Journal: JMIR Res Protoc Date: 2021-07-02