Detecting hidden confounding in observational data using multiple environments
This addresses a fundamental challenge in causal inference for researchers and practitioners who rely on observational data, though it is incremental as it builds on existing assumptions about independent causal mechanisms.
The paper tackles the problem of detecting hidden confounding in observational data by leveraging multiple datasets from different environments, and demonstrates that their proposed procedure correctly predicts the presence of hidden confounding in most cases, especially when the confounding bias is large.
A common assumption in causal inference from observational data is that there is no hidden confounding. Yet it is, in general, impossible to verify this assumption from a single dataset. Under the assumption of independent causal mechanisms underlying the data-generating process, we demonstrate a way to detect unobserved confounders when having multiple observational datasets coming from different environments. We present a theory for testable conditional independencies that are only absent when there is hidden confounding and examine cases where we violate its assumptions: degenerate & dependent mechanisms, and faithfulness violations. Additionally, we propose a procedure to test these independencies and study its empirical finite-sample behavior using simulation studies and semi-synthetic data based on a real-world dataset. In most cases, the proposed procedure correctly predicts the presence of hidden confounding, particularly when the confounding bias is large.