Efficient Estimation of the Complier General Causal Effect in Randomized Controlled Trials with One-Sided Noncompliance

2025-10-15

AI Summary

In randomized controlled trials (RCTs), one-sided noncompliance undermines randomization integrity and induces bias in conventional causal effect estimators. Method: This paper proposes the Complier General Causal Effect (CGCE) as a novel target parameter, providing its first rigorous definition within the potential outcomes framework and systematically deriving its efficient estimation conditions under minimal identification assumptions. The method integrates semiparametric efficiency theory with robust estimation strategies to ensure unbiasedness and high efficiency under noncompliance. Results: Simulation studies and empirical analyses demonstrate that the CGCE estimator achieves substantially improved estimation accuracy and stability compared to traditional approaches such as the Local Average Treatment Effect (LATE). By accommodating realistic noncompliance patterns, CGCE enhances both the applicability and reliability of causal inference in RCTs.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

A randomized controlled trial (RCT) is widely regarded as the gold standard for assessing the causal effect of a treatment or intervention, assuming perfect implementation. In practice, however, randomization can be compromised for various reasons, such as one-sided noncompliance. In this paper, we address the issue of one-sided noncompliance and propose a general estimand, the complier general causal effect (CGCE), to characterize the causal effect among compliers. We further investigate the conditions under which efficient estimation of the CGCE can be achieved under minimal assumptions. Comprehensive simulation studies and a real data application are conducted to illustrate the proposed methods and to compare them with existing approaches.

Problem

• Estimating causal effects with one-sided noncompliance in RCTs
• Proposing complier general causal effect for complier populations
• Achieving efficient CGCE estimation under minimal assumptions

Innovation

• Proposes complier general causal effect estimand
• Achieves efficient estimation under minimal assumptions
• Validates through simulations and real data