Lesser M L
Stat Med. 1982 Jul-Sep;1(3):277-80. doi: 10.1002/sim.4780010309.
Equal allocation of patients to treatment in a randomized clinical trial may have disadvantages ethically if the new treatment is believed to be at least as beneficial as the standard treatment. Others have considered, in a non-sequential setting, unbalanced randomized designs which allocate fewer patients to the potentially inferior standard treatment. This paper examines unbalanced randomized designs in a sequential comparison of two exponential survival distributions using the progressively censored Savage test. The results reveal no substantial sacrifice in asymptotic power or early stopping properties.
在随机临床试验中，如果新疗法被认为至少与标准疗法一样有益，那么在伦理上患者的平等分配治疗可能存在劣势。其他人在非序贯设置中考虑了不平衡随机设计，即将较少的患者分配到可能较差的标准治疗组。本文使用逐步删失的萨维奇检验，在两个指数生存分布的序贯比较中研究不平衡随机设计。结果表明，在渐近功效或早期停止特性方面没有实质性的牺牲。
