A potential outcomes approach to selection bias

TL;DR

This paper introduces a new, nonparametric potential outcomes framework for defining and analyzing selection bias in epidemiology, unifying structural and traditional views and simplifying bias assessment.

Contribution

It presents a novel potential outcomes-based definition of selection bias applicable to various epidemiological study designs and links bias analysis directly to causal effect estimation.

Findings

Provides a unified framework for structural and traditional selection bias

Enables analysis of confounding and selection bias simultaneously

Simplifies bias analysis in matched and case-cohort studies

Abstract

We propose a novel definition of selection bias in analytic epidemiology using potential outcomes. This definition captures selection bias under both the structural approach (where conditioning on selection into the study opens a noncausal path from exposure to disease in a directed acyclic graph) and the traditional definition (where a given measure of association differs between the study sample and the population eligible for inclusion). It is nonparametric, and selection bias under this approach can be analyzed using single-world intervention graphs both under and away from the null hypothesis. It allows the simultaneous analysis of confounding and selection bias, it explicitly links the selection of study participants to the estimation of causal effects using study data, and it can be adapted to handle selection bias in descriptive epidemiology. Through examples, we show that this approach provides a novel perspective on the variety of mechanisms that can generate selection bias and simplifies the analysis of selection bias in matched studies and case-cohort studies.