Sonja Swanson

Contributions to Public Health

• Improving causal inference methods: My research focuses on developing, improving, and increasing the transparency of methods for causal inference in epidemiologic studies. To learn what works to improve public health, I often use these methods in settings for which randomized trials are not feasible and for learning how to improve health in populations who have been excluded from randomized trials. As causal inferences from epidemiologic studies require unverifiable assumptions, much of my methodologic work has focused on understanding the robustness of effect estimates to plausible violations of the assumptions and how to triangulate approaches that rely on different assumptions.
  • Swanson SA, Hernán MA, Miller M, Robins JM, Richardson TS. Partial identification of the average treatment effect using instrumental variables: review of methods for binary instruments, treatments, and outcomes. Journal of the American Statistical Association. 2018;113(522):933-47.
  • Diemer EW, Labrecque J, Tiemeier H, Swanson SA. Application of the instrumental inequalities to a Mendelian randomization study with multiple proposed instruments. Epidemiology. 2020;31(1):65-74.
• Teaching causal inference: I work to make the use and interpretation of causal inference methods accessible to all health researchers and consumers of health research. When teaching, I emphasize question-asking as foundational to what we do: that is, we should ask, and attempt to answer, unambiguous questions about the extent to which different treatment or policy strategies may improve population health.
  • Labrecque JA, Swanson SA. Target trial emulation: Teaching epidemiology and beyond. European Journal of Epidemiology. 2017;32:473-5.
  • Rojas-Saunero LP, Young JG, Didelez V, Ikram MA, Swanson SA. Considering questions before methods in dementia research with competing events and causal goals. American Journal of Epidemiology. 2023;192(8):1415-23.
  • Swanson SA. The causal effects of causal inference pedagogy. Epidemiology. 2023;34(5):611-3.
• Causal inference in action: I collaborate widely to inform health-related decision-making, and especially in settings for which a randomized trial is not feasible and empirically informed decision-making necessarily relies on observational data. Much of my recent work has been on suicide prevention.
  • Studdert DM, Zhang Y, Swanson SA, Prince L, Rodden JA, Holsinger EE, Spittal MJ, Wintemute GJ, Miller M. Handgun ownership and suicide in California. New England Journal of Medicine. 2020;382(23):2220-9.
  • Swanson SA, Studdert DM, Zhang Y, Prince L, Miller M. Handgun divestment and risk of suicide. Epidemiology. 2023;34(1):99-106.