Neyman Jackknife: Design-Based Variance Estimation for Causal Inference under Interference

TL;DR

The paper introduces the Neyman Jackknife, a flexible framework for conservative variance estimation in causal inference under interference, applicable to various settings and outperforming some specialized methods.

Contribution

It presents a general, reusable variance estimation method for causal inference under interference, extending classical estimators and demonstrating superior performance in experiments.

Findings

Framework recovers classical estimators like Neyman and Newey-West under specific conditions.

Numerical experiments show the method matches or surpasses specialized baselines.

Applicable to a wide range of causal inference scenarios with interference.

Abstract

We propose a framework, the Neyman Jackknife, for conservative variance estimation in finite-population causal inference under interference. Our approach provides a general, flexible blueprint that enables conservative variance estimation whenever we are able to recompute our target estimator with some treatment assignments omitted. In classical settings, our approach recovers estimators closely related to the Neyman estimator under SUTVA and the Newey-West HAC variance estimator for time series. Numerical experiments suggest that our general-purpose framework yields variance estimators that can match or even surpass the performance of baselines that were purpose-built for specific applications.