Auto-G-Computation of Causal Effects on a Network

TL;DR

This paper introduces a novel statistical method called auto-g-computation for estimating causal effects in network data where interference and dependence are arbitrary and complex, extending traditional causal inference techniques.

Contribution

It develops a new approach for causal inference on networks that accounts for arbitrary interference and long-range dependence, relaxing key assumptions of traditional methods.

Findings

Enables causal effect estimation in complex network settings.

Provides a tractable inference method under network chain graph models.

Generalizes Robins' g-computation algorithm to network data.

Abstract

Methods for inferring average causal effects have traditionally relied on two key assumptions: (i) the intervention received by one unit cannot causally influence the outcome of another; and (ii) units can be organized into non-overlapping groups such that outcomes of units in separate groups are independent. In this paper, we develop new statistical methods for causal inference based on a single realization of a network of connected units for which neither assumption (i) nor (ii) holds. The proposed approach allows both for arbitrary forms of interference, whereby the outcome of a unit may depend on interventions received by other units with whom a network path through connected units exists; and long range dependence, whereby outcomes for any two units likewise connected by a path in the network may be dependent. Under network versions of consistency and no unobserved confounding, inference is made tractable by an assumption that the network's outcome, treatment and covariate vectors are a single realization of a certain chain graph model. This assumption allows inferences about various network causal effects via the auto-g-computation algorithm, a network generalization of Robins' well-known g-computation algorithm previously described for causal inference under assumptions (i) and (ii).