国家天元数学中部中心随机分析Colloquium系列报告 | 张立新 教授(浙江大学)

发布时间: 2023-03-19 20:08

报告目:Asymptotic Properties of Covariate-Adaptive Randomization in Clinical Trials

报告时间:2023-03-25  11:00-12:00

报告人:张立新 教授 浙江大学

报告地点:理学院东北楼四楼报告厅

报告摘要:Balancing treatment allocation over influential covariates is an important issue in clinical trials. In literature, a lot of covariate-adaptive randomization (CAR) procedures are proposed for balancing covariates. However, most studies have focused on balancing of discrete covariates. Applications of CAR for balancing continuous covariates remain comparatively rare.  In this talk, we consider a general framework of CAR procedures which can balance general covariate features, such as quadratic and interaction terms which can be discrete, continuous and mixing. We show that the proposed procedures have superior balancing properties; in particular, the convergence rate of imbalance vectors can attain the best rate O_p (1) for discrete covariates, continuous covariates or combinations of both discrete and continuous covariates, and at the same time, the convergence rate of the imbalance  of unobserved covariates is  O_p (√n),where n is the sample size. As an application, the asymptotic properties of the test for the treatment effects are established. The talk is based on works of Hu, Ye and Zhang (2022), Ma, Li, Zhang and Hu (2022), Zhang (2023).