Spatial Interference Detection in Treatment Effect Model

TL;DR

This paper introduces a novel low-rank and sparse model for detecting interference effects in treatment effect analysis, providing data-driven identification and testing methods with theoretical guarantees and practical demonstrations.

Contribution

It proposes a new data-driven approach for identifying interference effects using a low-rank and sparse model, along with estimation, testing, and detection algorithms.

Findings

The method accurately detects interference locations in simulations.

Theoretical bounds and guarantees are established for estimation and detection.

Real data examples demonstrate practical effectiveness.

Abstract

Modeling the interference effect is an important issue in the field of causal inference. Existing studies rely on explicit and often homogeneous assumptions regarding interference structures. In this paper, we introduce a low-rank and sparse treatment effect model that leverages data-driven techniques to identify the locations of interference effects. A profiling algorithm is proposed to estimate the model coefficients, and based on these estimates, global test and local detection methods are established to detect the existence of interference and the interference neighbor locations for each unit. We derive the non-asymptotic bound of the estimation error, and establish theoretical guarantees for the global test and the accuracy of the detection method in terms of Jaccard index. Simulations and real data examples are provided to demonstrate the usefulness of the proposed method.