Statistical Analysis of Censored Data Due to Detection Limits

讲座题目：Statistical Analysis of Censored Data Due to Detection Limits
讲座时间 Datetime:2025年6月30日，周一，16：00-19：00
地点 Venue: 中大珠海校区海琴二号A457
主持人 Host：赵育林 教授
报告人 Speaker: 贺华 教授
单位 Affiliation: 杜兰大学
报告摘要 Abstract:
Measures of substance concentration in urine, serum or other biological matrices often have an assay limit of detection. When concentration levels fall below the limit, the exact measures cannot be obtained, and thus are left censored. Common practices for handling censored data, either replacing the censored data with a constant value or deleting the censored data, often yield biased and/or inefficient estimates. The problems become more challenging when the censored data come from heterogenous populations consisting of exposure and non-exposure subpopulations.  When the censored data comes from non-exposed subjects, their measures are not observed and thus form a latent class resulting from a different censoring mechanism than that involved with exposed subjects 
In this talk, I will introduce several statistical tests to detect latent classes in censored data and discuss analysis strategies when censored variables serve as outcomes or predictors. Simulation results and real-world examples will be presented to illustrate the methods, along with practical guidelines for handling data censored due to detection limits.
报告人简介：
贺华博士是杜兰大学流行病和生物统计与数据科学系正教授。其研究聚焦混合群体建模、因果推断、纵向数据分析、半参数与非参数方法、ROC分析，以及统计方法在医学与公共卫生研究中的应用。她已发表120余篇论文，并作为首席研究员、合作研究员或生物统计学家参与多项美国国立卫生研究院（NIH）及基金会资助项目。贺博士合作撰写了研究生教材《应用分类与计数数据分析》（查普曼&霍尔/CRC出版社），并联合主编《统计因果推断及其在公共卫生研究中的应用》（斯普林格出版社）。 贺华博士现任杜兰大学转化科学研究所（TUTSI）临床研究核心实验室联席主任及方法学/生物统计学部门主任，同时担任《美国公共卫生杂志》（AJPH）统计副主编。加入杜兰大学前，贺博士曾任罗切斯特大学助理教授，并在该校获得统计学硕士与博士学位。