THE DOUBLY ADAPTIVE BIASED COIN DESIGN FOR SEQUENTIAL CLINICAL-TRIALS

被引：101

作者：

EISELE, JR ^{[1
]}

机构：

[1] UNIV WISCONSIN,DEPT BIOSTAT,MADISON,WI 53706

来源：

JOURNAL OF STATISTICAL PLANNING AND INFERENCE | 1994年 / 38卷 / 02期

关键词：

BIASED COIN DESIGNS; EXPONENTIAL FAMILIES; SEQUENTIAL PROCEDURE; STOPPING RULE; STRONG LAW OF LARGE NUMBERS;

D O I：

10.1016/0378-3758(94)90038-8

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

A biased coin design is proposed for the allocation of subjects to treatments A and B in a clinical trial when the desired allocation proportions are unknown. The design is doubly adaptive in the sense that it takes account of the proportion of subjects assigned to each treatment and the current estimate of the desired allocation proportion. A strong law of large numbers is established for the proportion of subjects assigned to a treatment when subject responses are independent random variables from standard exponential families. The normal case is presented as an application.

引用

页码：249 / 261

页数：13

共 6 条

[1]

BROWN LD, 1986, FUNDAMENTALS STATIST

[2]

Chow Y S., 1988, PROBABILITY THEORY I, P338, DOI [10.1007/978-1-4684-0504-0, DOI 10.1007/978-1-4684-0504-0]

[3]

EFRON B, 1971, BIOMETRIKA, V58, P403, DOI 10.2307/2334377

[4]

EISELE J, 1990, SEQUENTIAL ANAL, V9, P343

[5] A SEQUENTIAL ANALOGUE OF BEHRENS-FISHER PROBLEM [J].

ROBBINS, H ;

SIMONS, G ;

STARR, N .

ANNALS OF MATHEMATICAL STATISTICS, 1967, 38 (05) :1384-&

[6] ADAPTIVE BIASED COIN DESIGN FOR SEQUENTIAL EXPERIMENTS [J].

WEI, LJ .

ANNALS OF STATISTICS, 1978, 6 (01) :92-100

← 1 →