Mediation Analysis for Probabilities of Causation
This work addresses the need for more precise causal inference in fields like psychology, though it appears incremental as it builds on existing probabilities of causation concepts.
The paper tackled the problem of quantifying causal pathways in mediation analysis by introducing new variants of probabilities of causation, such as controlled direct and natural direct/indirect measures, and developed identification theorems to estimate them from observational data, demonstrating application on a real-world psychology dataset.
Probabilities of causation (PoC) offer valuable insights for informed decision-making. This paper introduces novel variants of PoC-controlled direct, natural direct, and natural indirect probability of necessity and sufficiency (PNS). These metrics quantify the necessity and sufficiency of a treatment for producing an outcome, accounting for different causal pathways. We develop identification theorems for these new PoC measures, allowing for their estimation from observational data. We demonstrate the practical application of our results through an analysis of a real-world psychology dataset.