CKH: Causal Knowledge Hierarchy for Estimating Structural Causal Models from Data and Priors

Causal inference involving Structural causal models (SCMs) provides a principled approach to identifying causation from observational and experimental data in disciplines ranging from economics to medicine. However, to estimate the underlying causal structure, SCMs need to rely on domain knowledge in addition to available data. Clinical research has a vast collection of well-explored hypotheses, experiments, and publications, rich with underused causal information. A key challenge in this context is the absence (or acceptance) of a systematic and methodological framework for encoding priors (background knowledge) into causal models. We propose an abstraction called causal knowledge hierarchy (CKH) for encoding priors into causal models. Our approach is based on the foundation of "levels of evidence" in medicine, with a focus on confidence in causal information. Using CKH, we present a standardized framework for encoding causal priors from various information sources and combining them to derive an SCM. We evaluate our approach on multiple (simulated and real-world) benchmark datasets and demonstrate overall performance compared to the ground truth causal model.