🤖 AI Summary
This paper addresses the validity of negative control variable (NCV) falsification tests in instrumental variable (IV) design. We identify a critical flaw: conventional NCV tests implicitly impose untestable functional-form restrictions—beyond standard exclusion and independence assumptions—leading to false rejection of valid IVs. To resolve this, we develop a unified theoretical framework that formally characterizes the identification conditions required for NCVs and establishes principled variable selection criteria. We further uncover and correct the implicit assumption bias inherent in existing NCV tests, proposing robust implementation guidelines. Methodologically, our approach integrates causal inference, IV identification theory, and conditional independence testing. The resulting framework substantially enhances the robustness, interpretability, and empirical reliability of IV analyses.
📝 Abstract
The validity of instrumental variable (IV) designs is typically tested using two types of falsification tests. We characterize these tests as conditional independence tests between negative control variables -- proxies for unobserved variables posing a threat to the identification -- and the IV or the outcome. We describe the conditions that variables must satisfy in order to serve as negative controls. We show that these falsification tests examine not only independence and the exclusion restriction, but also functional form assumptions. Our analysis reveals that conventional applications of these tests may flag problems even in valid IV designs. We offer implementation guidance to address these issues.
