Robertson David S, Glimm Ekkehard
MRC Biostatistics Unit, University of Cambridge, Cambridge, UK.
Novartis Pharma AG, Novartis Campus, Basel, Switzerland.
Commun Stat Theory Methods. 2018 Jan 5;48(3):616-627. doi: 10.1080/03610926.2017.1417429. eCollection 2019.
To efficiently and completely correct for selection bias in adaptive two-stage trials, uniformly minimum variance conditionally unbiased estimators (UMVCUEs) have been derived for trial designs with normally distributed data. However, a common assumption is that the variances are known exactly, which is unlikely to be the case in practice. We extend the work of Cohen and Sackrowitz (, 8(3):273-278, 1989), who proposed an UMVCUE for the best performing candidate in the normal setting with a common variance. Our extension allows for multiple selected candidates, as well as unequal stage one and two sample sizes.
为了在适应性两阶段试验中有效且完全地校正选择偏倚，针对具有正态分布数据的试验设计，已经推导出了一致最小方差条件无偏估计量（UMVCUEs）。然而，一个常见的假设是方差是精确已知的，而在实际中不太可能如此。我们扩展了科恩和萨克罗维茨（Cohen and Sackrowitz，《统计与概率快报》，8(3):273 - 278，1989）的工作，他们针对具有共同方差的正态设定下表现最佳的候选者提出了一个UMVCUE。我们的扩展允许有多个选定的候选者，以及第一阶段和第二阶段样本量不相等的情况。
