具有一般反应的自适应临床设计的渐近推断(英文)  

Asymptotic Inference for Response-Adaptive Clinical Trial Design with General Outcomes

作　　者：朱春华[1] 陈桂景[2] 

机构地区：[1]中国科学技术大学统计与金融系,安徽合肥230026 [2]安徽大学数学系,安徽合肥230039

出　　处：《中国科学技术大学学报》2005年第6期789-795,共7页JUSTC

基　　金：Supported by National Natural Science Foundation of China (10271001) .

摘　　要：研究了具有连续反应的临床试验.首先应用线性秩统计量的渐近理论,获得由Rosenberger提出的无差异治疗效果假设检验统计量的渐近正态性;然后给出一种新的设计且获得相应统计量的渐近正态性.We consider the clinical trial with a continuous treatment response. First, applying the properties of the linear rank statistic, we obtain the asymptotic normality of the test statistic which is based on rank statistic proposed by Rosenberger and used to test the hypothesis of no treatment effect for a trial with continuous response. Then, we propose another assignment scheme for the trial with continuous response and obtain the asymptotic normality of the corresponding test statistic.

关 键 词：随机优胜者优先原则 置换检验 线性秩统计量 渐近正态性 

分 类 号：O212.7[理学—概率论与数理统计]