Graphical Models for Inference Under Outcome-Dependent Sampling

TL;DR

This paper explores how graphical models can be used to understand and analyze data collected through outcome-dependent sampling, such as case-control studies, by explicitly modeling the sampling process and its implications for causal inference.

Contribution

It introduces a framework for incorporating sampling indicators into graphical models to assess the feasibility of estimating associations and causal effects under outcome-dependent sampling.

Findings

Graphical conditions for consistent estimation of exposure-outcome associations.

Conditions for testing and estimating causal effects in outcome-dependent sampling.

Practical examples demonstrating the application of the proposed methods.

Abstract

We consider situations where data have been collected such that the sampling depends on the outcome of interest and possibly further covariates, as for instance in case-control studies. Graphical models represent assumptions about the conditional independencies among the variables. By including a node for the sampling indicator, assumptions about sampling processes can be made explicit. We demonstrate how to read off such graphs whether consistent estimation of the association between exposure and outcome is possible. Moreover, we give sufficient graphical conditions for testing and estimating the causal effect of exposure on outcome. The practical use is illustrated with a number of examples.