Average Controlled and Average Natural Micro Direct Effects in Summary Causal Graphs

TL;DR

This paper explores the conditions under which average controlled and natural direct effects can be identified from summary causal graphs, especially in complex, non-linear, and hidden confounded systems.

Contribution

It provides sufficient (and in some cases necessary) conditions for identifying direct effects from summary causal graphs in non-parametric, real-world scenarios.

Findings

Identifies sufficient conditions for effect identifiability.

Shows conditions are necessary in confound-free cases.

Addresses challenges in non-linear, real-world causal inference.

Abstract

In this paper, we investigate the identifiability of average controlled direct effects and average natural direct effects in causal systems represented by summary causal graphs, which are abstractions of full causal graphs, often used in dynamic systems where cycles and omitted temporal information complicate causal inference. Unlike in the traditional linear setting, where direct effects are typically easier to identify and estimate, non-parametric direct effects, which are crucial for handling real-world complexities, particularly in epidemiological contexts where relationships between variables (e.g, genetic, environmental, and behavioral factors) are often non-linear, are much harder to define and identify. In particular, we give sufficient conditions for identifying average controlled micro direct effect and average natural micro direct effect from summary causal graphs in the presence of hidden confounding. Furthermore, we show that the conditions given for the average controlled micro direct effect become also necessary in the setting where there is no hidden confounding and where we are only interested in identifiability by adjustment.