Path-specific Effects Based on Information Accounts of Causality
This work addresses a theoretical problem in causal inference for researchers and practitioners in fairness analysis, offering a more interpretable and less restrictive approach compared to existing methods.
The paper tackles the challenge of defining path-specific effects in mediation analysis by proposing a new path intervention method based on information accounts of causality, which explicitly describes manipulations in structural causal models and does not require the non-existence of a recanting witness for identification.
Path-specific effects in mediation analysis provide a useful tool for fairness analysis, which is mostly based on nested counterfactuals. However, the dictum ``no causation without manipulation'' implies that path-specific effects might be induced by certain interventions. This paper proposes a new path intervention inspired by information accounts of causality, and develops the corresponding intervention diagrams and $π$-formula. Compared with the interventionist approach of Robins et al.(2020) based on nested counterfactuals, our proposed path intervention method explicitly describes the manipulation in structural causal model with a simple information transferring interpretation, and does not require the non-existence of recanting witness to identify path-specific effects. Hence, it could serve useful communications and theoretical focus for mediation analysis.