Robust Identification in Randomized Experiments with Noncompliance

TL;DR

This paper develops methods to identify causal effects in randomized experiments with noncompliance when traditional IV assumptions are violated, providing sharp bounds and applying them to real data.

Contribution

It introduces robust identification strategies under weaker assumptions than standard IV, deriving sharp bounds for causal parameters.

Findings

Standard LATE assumptions are incompatible in the case study.

Sharp bounds on causal effects are derived under relaxed assumptions.

Application demonstrates the practical relevance of the robust bounds.

Abstract

Instrument variable (IV) methods are widely used in empirical research to identify causal effects of a policy. In the local average treatment effect (LATE) framework, the IV estimand identifies the LATE under three main assumptions: random assignment, exclusion restriction, and monotonicity. However, these assumptions are often questionable in many applications, leading some researchers to doubt the causal interpretation of the IV estimand. This paper considers a robust identification of causal parameters in a randomized experiment setting with noncompliance where the standard LATE assumptions could be violated. We discuss identification under two sets of weaker assumptions: random assignment and exclusion restriction (without monotonicity), and random assignment and monotonicity (without exclusion restriction). We derive sharp bounds on some causal parameters under these two sets of relaxed LATE assumptions. Finally, we apply our method to revisit the random information experiment conducted in Bursztyn, Gonz\'alez, and Yanagizawa-Drott (2020) and find that the standard LATE assumptions are jointly incompatible in this application. We then estimate the robust identified sets under the two sets of relaxed assumptions.