Air Pollution and Hospital Admissions for Heart Disease in Eight U.S. Counties

TLDR

Causal diagrams have long been used informally and are now formally developed for expert systems, robotics, and epidemiologic research, offering a starting point for identifying necessary variables and critically evaluating confounding criteria. The authors aim to introduce recent formal developments of causal diagrams and to demonstrate how to modify traditional confounding criteria. They provide an introductory framework for applying causal diagrams in epidemiologic studies and illustrate how to adjust confounding criteria accordingly. The analysis reveals previously unnoticed shortcomings in traditional confounding criteria when multiple potential confounders are considered.

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.