题 目：Sample Size and Power Calculations with Win Measures Based on Hierarchical Endpoints——In Memory of Professor Pan Wenxi
内容简介：Win measures, such as win ratio, win odds, net benefit, and desirability of outcome ranking (DOOR), have become popular approaches for the analysis of hierarchical endpoints in clinical studies. Sample size and power calculations with win measures based on hierarchical endpoints are often reliant on simulation studies, which can be cumbersome. Existing sample size and powerformulas require investigators to specify clinically significant and meaningful magnitudes of winmeasures and the probability of ties—a task that is challenging to elicit from prior publishedliterature or preliminary data. In this talk, we provide sample size and power calculation formulasfor the four aforementioned win measures. To facilitate formula-based sample size or power calculations, we offer formulas to compute overall win measures and the overall probability of ties. These can be derived using the specification of marginal win measures and marginal probability of ties, which are readily available from clinical investigators or literature. The latter formulas introduce a novel approach to specify meaningful and justifiable magnitudes of win measures and the probability of ties. Consequently, they can be readily employed to evaluate thestatistical power based on the number of multiple endpoints, their ordering, and types. Our extensive simulation studies demonstrate that the power estimations based on these formulas are often similar to the simulated powers for any type of correlated hierarchical endpoints. We illustrate the usefulness of our formulas by utilizing data from existing trials with different types of hierarchical endpoints.
报告人：HuimanXie Barnhart（谢慧满）
报告人简介：1983年获得华南师范大学数学学士学位，1986年获得暨南大学数学硕士学位，1992年获得匹兹堡大学统计学博士学位，1992-2003 年，担任埃默里大学生物统计系教授，2003 年至今，担任杜克大学生物统计与生物信息学系教授，目前是杜克大学的詹姆斯·B·杜克杰出教授，并担任该校生物统计与生物信息学系的副主席，负责指导和发展教职员工。她还是杜克临床研究所的主要成员。因其在可靠性评估、临床试验和队列研究的卓越领导能力、以及对下一代生物统计学家的教育和指导方面有影响力的贡献，她被授予美国统计协会会士荣誉。她目前拥有超过190 篇经过同行评审的期刊文章。她研究兴趣包括：统计方法学、临床试验设计方法、临床研究生物统计学，在肝损伤、心血管成像、放射学成像、心血管疾病、肾脏疾病、生殖医学、帕金森病、老龄化等多个临床领域开展的合作研究。她对教育、指导和研究的奉献将不断塑造着生物统计学领域。
时 间：2024年6月14日（周五）上午10：00开始
地 点：暨南大学石牌校区南海楼224数学系会议室
热烈欢迎广大师生参加!
信息科学技术学院
2024年6月5日