A Matching Based Theoretical Framework for Estimating Probability of Causation

TL;DR

This paper introduces a new theoretical framework to estimate the probability of causation from observational and experimental data, addressing limitations of existing methods and enhancing practical applicability.

Contribution

It provides a novel approach to estimate the distribution of probability of causation, applicable to observational data and overcoming previous operational constraints.

Findings

Framework can estimate PC distribution from observational data.

Illustrative examples show influence of sample size and event rarity.

Addresses limitations of existing operationalizations.

Abstract

The concept of Probability of Causation (PC) is critically important in legal contexts and can help in many other domains. While it has been around since 1986, current operationalizations can obtain only the minimum and maximum values of PC, and do not apply for purely observational data. We present a theoretical framework to estimate the distribution of PC from experimental and from purely observational data. We illustrate additional problems of the existing operationalizations and show how our method can be used to address them. We also provide two illustrative examples of how our method is used and how factors like sample size or rarity of events can influence the distribution of PC. We hope this will make the concept of PC more widely usable in practice.