Heterogeneous Treatment Effects under Network Interference: A Nonparametric Approach Based on Node Connectivity

TL;DR

This paper introduces a nonparametric, node-specific causal effect estimation method for network data, accounting for interference and network structure, demonstrated through microfinance application.

Contribution

It develops KECENI, a doubly robust, non-parametric estimator for node-wise effects under network interference, enhancing granularity in causal inference.

Findings

KECENI provides consistent, asymptotically normal estimates.

Network characteristics significantly influence treatment effects.

Application to microfinance data illustrates method's practical utility.

Abstract

In network settings, interference between units makes causal inference more challenging as outcomes may depend on the treatments received by others in the network. Typical estimands in network settings focus on treatment effects aggregated across individuals in the population. We propose a framework for estimating node-wise counterfactual means, allowing for more granular insights into the impact of network structure on treatment effect heterogeneity. We develop a doubly robust and non-parametric estimation procedure, KECENI (Kernel Estimator of Causal Effect under Network Interference), which offers consistency and asymptotic normality under network dependence. The utility of this method is demonstrated through an application to microfinance data, revealing the impact of network characteristics on treatment effects.