时间：2016年5月5日（周四）13:30

地点：下沙校区教学D楼210学术报告厅

摘要：

In clinical trial studies, adaptive-randomization is a popular method to randomize patients to treatments. Various adaptive-randomization procedures have been proposed for balancing treatments, for allocating more patients to better treatments, for maximizing the test power and various other purposes. In this talk, we introduce and compare several statistical models of adaptive-randomization procedures basing on our theory in this field.

References

Efron, B. (1971). Forcing a sequential experiment to be balanced. Biometrika, 62, 347-352.

Hu, F. and Zhang, L.-X. (2004). Asymptotic properties of doubly adaptive biased coin designs for multi-treatment clinical trials. Annals of Statistics, 32, 268-301

Hu, F., Zhang, L.-X. and He, X. (2009), Efficient randomized adaptive designs, Annals of Statistics, 37, 2543–2560.

Zhang, L.-X. (2016) , Central limit theorems of a recursive stochastic algorithm with applications to adaptive designs, Annals of Applied Probability, to appear.

专家简介：

张立新，浙江大学数学学院教授，副院长，国家杰出青年基金获得者，中国现场统计研究会理事、IMS-China委员会委员、浙江省数学会常务理事、浙江省现场统计研究会副理事长。主要从事概率极限理论、自适应设计、相依变量和随机过程的样本轨道性质等研究，研究成果获教育部科技进步奖二等奖等。