MULTIPLE TESTING PROCEDURE FOR CLINICAL-TRIALS
MULTIPLE TESTING PROCEDURE FOR CLINICAL-TRIALS
复制标题
DOI：
10.2307/2530245
复制
发表时间：
1979-01-01
期刊：
影响因子：
1.9
通讯作者：
FLEMING, TR
中科院分区：
文献类型：
--
作者：
OBRIEN, PC;FLEMING, TR
当对治疗的反应是二分法（即成功或失败）且立即发生时，建议采用多重测试程序来比较两种治疗方法。每个测试的建议测试统计量是基于该点收集的所有数据的通常 (Pearson).chi.2 统计量。测试的最大数量 (N) 和连续测试之间收集的观测值数量 (m1 + m2) 是预先确定的。该过程的总体规模的控制精度实际上与基于 N(m1 + m2) 观测值的单样本 χ2 检验相同。威力也几乎是一样的。当一种治疗效果明显优于另一种治疗时，通过提供提前终止的机会，多重测试程序可以消除临床试验中经常出现的道德困境。
A multiple testing procedure is proposed for comparing 2 treatments when response to treatment is both dichotomous (i.e., success or failure) and immediate. The proposed test statistic for each test is the usual (Pearson) .chi.2 statistic based on all data collected to that point. The maximum number (N) of tests and the number (m1 + m2) of observations collected between successive tests is fixed in advance. The overall size of the procedure is controlled with virtually the same accuracy as the single sample .chi.2 test based on N(m1 + m2) observations. The power is also virtually the same. By affording the opportunity to terminate early when 1 treatment performs markedly better than the other, the multiple testing procedure may eliminate the ethical dilemmas that often accompany clinical trials.