Causal Identification under Interference: The Role of Treatment Assignment Independence

TL;DR

This paper examines how standard causal identification methods can still be valid under interference if treatment assignment independence is assumed, providing a robustness framework for violations.

Contribution

It demonstrates that common identification formulas can identify meaningful causal effects under interference with certain treatment assignment restrictions.

Findings

Identification formulas target average direct effects under interference.

Results do not depend on knowing the interference structure.

A sensitivity analysis framework quantifies robustness to assignment dependence violations.

Abstract

Empirical researchers routinely invoke the no-interference or \textit{individualistic treatment response} (ITR) assumption to identify causal effects in observational studies, despite concerns that interference across units may arise in many economic settings. This paper studies the causal content of standard ITR-based identification formulas when arbitrary interference is present. We show that, under restrictions on dependence between treatment assignments across units, conventional ITR-based identification formulas -- including those underlying selection-on-observables, instrumental variables, regression discontinuity designs, and difference-in-differences -- identify well-defined causal objects: types of \textit{average direct effects} (ADEs). These results do not require knowledge of the interference structure or specification of exposure mappings. We also propose a sensitivity analysis framework that quantifies the robustness of statistical inference to violations of treatment-assignment independence under arbitrary interference.