Kraemer H C
Department of Psychiatry and Behavioral Sciences, Stanford University, CA 94305.
Psychopharmacol Bull. 1991;27(3):217-24.
The power of a randomized clinical trial (RCT) depends on two factors: sample size and effect size. Most psychiatric research design strategies focus on increasing sample size, despite major problems in recruiting large numbers of subjects or funding such costly studies. It is possible to increase power in RCTs in a variety of ways without increasing sample size, in essence by increasing effect size by decreasing within-group variance. Such strategies are presented and discussed.
随机临床试验（RCT）的效力取决于两个因素：样本量和效应量。尽管在招募大量受试者或资助此类成本高昂的研究方面存在重大问题，但大多数精神病学研究设计策略仍侧重于增加样本量。在不增加样本量的情况下，有多种方法可以提高RCT的效力，实质上是通过减少组内方差来增加效应量。本文将介绍并讨论这些策略。
