Causal Diagrams for Epidemiologic Research

TLDR

Causal diagrams have evolved from informal tools to formally developed models used in expert systems and robotics. The paper introduces these developments and their application to epidemiologic research. They provide a starting point for identifying variables that must be measured and controlled to obtain unconfounded effect estimates, and they offer a method for critically evaluating traditional epidemiologic confounding criteria. They uncover previously unnoticed shortcomings of traditional confounding criteria in multi‑confounder contexts and demonstrate how to modify these criteria to address the issues. Epidemiology 1999;10:37–48.

Abstract

Causal diagrams have a long history of informal use and, more recently, have undergone formal development for applications in expert systems and robotics. We provide an introduction to these developments and their use in epidemiologic research. Causal diagrams can provide a starting point for identifying variables that must be measured and controlled to obtain unconfounded effect estimates. They also provide a method for critical evaluation of traditional epidemiologic criteria for confounding. In particular, they reveal certain heretofore unnoticed shortcomings of those criteria when used in considering multiple potential confounders. We show how to modify the traditional criteria to correct those shortcomings. (Epidemiology 1999;10:37–48)