Transportability of Regression Calibration with External Validation Studies for Measurement Error Correction

2026-01-25

AI Summary

This study addresses measurement error correction in nutritional and environmental epidemiology, where external validation studies are commonly used but rely critically on transportability assumptions. Under a mixed Berkson-classical error model, the authors rigorously derive, for the first time, the precise transportability condition required for regression calibration to yield unbiased estimates. They further demonstrate that even when this condition is violated, the bias of the corrected estimator is typically substantially smaller than that of an uncorrected analysis. The validity of the derived condition and the practical superiority of regression calibration are confirmed through theoretical derivations, simulation studies, and an empirical application using data from the Health Professionals Follow-up Study, focusing on the association between moderate-intensity physical activity and cardiovascular disease.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Graphical Models
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

In nutritional and environmental epidemiology, exposures are impractical to measure accurately, while practical measures for these exposures are often subject to substantial measurement error. Regression calibration is among the most used measurement error correction methods with external validation studies. The use of external studies to assess the measurement error process always carries the risk of introducing estimation bias into the main study analysis. Although the transportability of regression calibration is usually assumed for practical epidemiology studies, it has not been well studied. In this work, under the measurement error process with a mixture of Berkson-like and classical-like errors, we investigate conditions under which the effect estimate from regression calibration with an external validation study is unbiased for the association between exposure and health outcome. We further examine departures from the transportability assumption, under which the regression calibration estimator is itself biased. However, we theoretically prove that, in most cases, it yields lower bias than the naive method. The derived conditions are confirmed through simulation studies and further verified in an example investigating the association between the risk of cardiovascular disease and moderate physical activity in the health professional follow-up study.

Problem

• transportability
• regression calibration
• measurement error
• external validation study
• epidemiology

Innovation

• transportability
• regression calibration
• measurement error correction
• external validation study
• Berkson-classical mixed error