报告题目：Extending the DeLong algorithm for comparing areas under receiving operating characteristic curves with missing data
报告人： Prof. Zou Guangyong
报告时间：2024年11月29日星期五上午10：30
报告地点：至善楼234
邀请人：邱世芳教授
报告摘要：
A diagnostic test or biomarker with high accuracy is vital to the practice of medicine. Accuracy is commonly quantified by the area under the receiver operating characteristic curve (AUC). A nonparametric method proposed by DeLong et al in 1988 for comparing correlated AUCs is used widely in practice, with the paper received over 20,000 times. However, the DeLong method as implemented in popular software quietly deletes individuals with any missing values, yielding potentially invalid and/or inefficient results. In this talk, I will discuss how to simplify the DeLong algorithm using ranks and extend it to accommodate missing data by using a mixed model approach for multivariate data. Simulation results demonstrate the validity and efficiency of our procedure for data missing at random. I will also illustrate our proposed procedure in SAS, Stata, and R using the original DeLong data.
报告人简介：
邹光勇，教授，博士生导师，加拿大西安大略大学医学院生物统计学教授，罗伯茨临床试验有限公司生物统计学部主任。1992年在大麦吉尔大学获土壤学硕士学位，1998年在康乃狄克大学同时获得数理统计学硕士学位和植物学博士学位，2002年在西安大略大学获生物统计学博士学位。邹教授一直从事临床试验统计方法的研究，已在American Journal of Epidemiology, Statistics in Medicine, Biometrics等国际重要学术刊物上发表了200余篇高水平学术论文，很多文章被广泛引用（总引用次数高达30000多次，h-index:58, i10-index: 135)，其中，发表在American Journal of Epidemiology的一篇文章被引用了8000次。他目前的研究侧重于肠道炎症疾病的临床试验统计研究，特别是试验设计和分析方面的研究。
主办单位：国际交流与合作处
承办单位：理学院、数学科学研究中心
