On Associative Confounder Bias

TL;DR

This paper examines the complex role of variables associated with confounders in causal inference, highlighting potential errors in common practices and proposing strategies for better variable selection to reduce bias.

Contribution

It clarifies when including or excluding variables associated with confounders is appropriate, offering guidance for more accurate causal effect estimation.

Findings

Including non-causal variables can sometimes introduce bias.

Excluding relevant confounders can lead to incorrect causal estimates.

Proper variable selection depends on context and aims to minimize bias.

Abstract

Conditioning on some set of confounders that causally affect both treatment and outcome variables can be sufficient for eliminating bias introduced by all such confounders when estimating causal effect of the treatment on the outcome from observational data. It is done by including them in propensity score model in so-called potential outcome framework for causal inference whereas in causal graphical modeling framework usual conditioning on them is done. However in the former framework, it is confusing when modeler finds a variable that is non-causally associated with both the treatment and the outcome. Some argue that such variables should also be included in the analysis for removing bias. But others argue that they introduce no bias so they should be excluded and conditioning on them introduces spurious dependence between the treatment and the outcome, thus resulting extra bias in the estimation. We show that there may be errors in both the arguments in different contexts. When such a variable is found neither of the actions may give the correct causal effect estimate. Selecting one action over the other is needed in order to be less wrong. We discuss how to select the better action.