Confounder Selection: Objectives and Approaches

TL;DR

This paper reviews various criteria and approaches for confounder selection in observational studies, discussing their objectives, assumptions, limitations, and practical implications to guide researchers.

Contribution

It provides a comprehensive, unified review of confounder selection criteria, analyzing their objectives, assumptions, and practical limitations in observational study design.

Findings

Different confounder selection methods have varying objectives and assumptions.

Many methods require different levels of structural knowledge.

Limitations of existing approaches impact their practical application.

Abstract

Confounder selection is perhaps the most important step in the design of observational studies. A number of criteria, often with different objectives and approaches, have been proposed, and their validity and practical value have been debated in the literature. Here, we provide a unified review of these criteria and the assumptions behind them. We list several objectives that confounder selection methods aim to achieve and discuss the amount of structural knowledge required by different approaches. Finally, we discuss limitations of the existing approaches and implications for practitioners.