Identifiability of Direct Effects from Summary Causal Graphs

TL;DR

This paper characterizes when direct causal effects can be identified from summary causal graphs that omit temporal details, providing criteria and methods for estimation in such cases.

Contribution

It offers a complete graphical criterion for the identifiability of direct effects from summary causal graphs and proposes two finite adjustment sets for estimation.

Findings

Complete characterization of identifiability conditions.

Two sound finite adjustment sets for effect estimation.

Applicability to cases with cycles and missing temporal info.

Abstract

Dynamic structural causal models (SCMs) are a powerful framework for reasoning in dynamic systems about direct effects which measure how a change in one variable affects another variable while holding all other variables constant. The causal relations in a dynamic structural causal model can be qualitatively represented with an acyclic full-time causal graph. Assuming linearity and no hidden confounding and given the full-time causal graph, the direct causal effect is always identifiable. However, in many application such a graph is not available for various reasons but nevertheless experts have access to the summary causal graph of the full-time causal graph which represents causal relations between time series while omitting temporal information and allowing cycles. This paper presents a complete identifiability result which characterizes all cases for which the direct effect is graphically identifiable from a summary causal graph and gives two sound finite adjustment sets that can be used to estimate the direct effect whenever it is identifiable.