BIMSA >
BIMSA 数字经济实验室讨论班
BIMSA 数字经济实验室讨论班
Causal inference for the effects of mismeasured covariates through double/debiased machine learning
Causal inference for the effects of mismeasured covariates through double/debiased machine learning
演讲者
汪作蘅
时间
2026年10月23日 15:00 至 17:00
地点
A7-201
线上
Zoom 242 742 6089
(BIMSA)
摘要
One way to quantify exposure to air pollution and its constituents in epidemiologic studies is to use an individual’s nearest monitor. This strategy results in potential inaccuracy in the actual personal exposure, introducing bias in estimating the health effects of air pollution and its constituents, especially when evaluating the causal effects of correlated multi-pollutant constituents measured with correlated error. This paper addresses estimation and inference for the causal effect of one constituent in the presence of other PM2.5 constituents, accounting for measurement error and correlations. We used a linear regression calibration model in an external validation study, and extended a double/debiased machine learning (DML) approach to correct for measurement error and estimate the effect of interest in the main study. We demonstrated that the DML estimator with regression calibration is consistent and derived its asymptotic variance. Simulations showed that the proposed estimator reduced bias and attained nominal coverage probability across most simulation settings. We applied this method to assess the causal effects of PM2.5 constituents on cognitive function in the Nurses’ Health Study and identified two PM2.5 constituents, Br and Mn, that showed a negative causal effect on cognitive function after measurement error correction.
演讲者介绍
Dr. Wang is a Professor of Biostatistics, Computational Biology and Bioinformatics, and Biomedical Informatics & Data Science at Yale University. Her research focuses on statistical modeling of omics and healthcare data. Dr. Wang’s statistical expertise spans kernel machine methods, mixed effects models, correlated and longitudinal data analysis, machine learning, and network analysis. She develops innovative statistical methods and computational tools for large-scale biomedical studies and electronic health records data, including disease risk prediction, genetic susceptibility variant identification, and single-cell and spatial transcriptomic data analysis, with application in mental health, addiction, cancer, autism, lung and cardiovascular diseases, contributing to the understanding of disease pathogenesis.