Identifiability in Causal Abstractions: A Hierarchy of Criteria

TL;DR

This paper develops a hierarchical framework of criteria for determining the identifiability of causal effects within collections of causal diagrams, addressing challenges when full causal knowledge is unavailable.

Contribution

It introduces a structured hierarchy of identifiability criteria for causal abstractions, clarifying their relationships and applicability in complex, high-dimensional settings.

Findings

Hierarchical organization of identifiability criteria.

Framework applicable to partial causal knowledge.

Tools for reasoning about causal identifiability.

Abstract

Identifying the effect of a treatment from observational data typically requires assuming a fully specified causal diagram. However, such diagrams are rarely known in practice, especially in complex or high-dimensional settings. To overcome this limitation, recent works have explored the use of causal abstractions-simplified representations that retain partial causal information. In this paper, we consider causal abstractions formalized as collections of causal diagrams, and focus on the identifiability of causal queries within such collections. We introduce and formalize several identifiability criteria under this setting. Our main contribution is to organize these criteria into a structured hierarchy, highlighting their relationships. This hierarchical view enables a clearer understanding of what can be identified under varying levels of causal knowledge. We illustrate our framework through examples from the literature and provide tools to reason about identifiability when full causal knowledge is unavailable.