Müller Johannes, Manz Rolf, Hoyer Jürgen
Institut für Klinische, Diagnostische und Differentielle Psychologie, Technische Universität Dresden, Germany.
Psychother Psychosom Med Psychol. 2002 Sep-Oct;52(9-10):408-16. doi: 10.1055/s-2002-34288.
This article deals with the issue of statistical validity when evaluating interventions. The most common study design with two groups and two points of measurement is discussed. In clinical research settings, unsatisfactory statistical validity is often seen due to small sample sizes. In order to resolve this problem, a strategy based on an approach by Hager is proposed which takes both significance testing and effects sizes systematically into account. Using an example from clinical research practice the problematic issue of statistical power is introduced and methods to increase the power of tests are discussed. Within this framework, Erdfelder's compromise power analysis (computing alpha levels according to a predetermined beta/alpha error ratio) is crucial as well as a lowering of the number of applied tests by data reduction and the improved detection of potential effects by methods to reduce error variance. The results show that significance tests should not be used in case of small sample and effect sizes. In these cases different approaches should be used.
本文探讨了评估干预措施时的统计有效性问题。文中讨论了最常见的两组两点测量的研究设计。在临床研究环境中，由于样本量小，统计有效性往往不尽人意。为了解决这个问题，提出了一种基于哈格方法的策略，该策略系统地考虑了显著性检验和效应量。通过临床研究实践中的一个例子，介绍了统计功效的问题，并讨论了提高检验功效的方法。在此框架内，埃尔德费尔德的折衷功效分析（根据预定的β/α错误率计算α水平）至关重要，同时通过数据简化减少应用检验的数量以及通过减少误差方差的方法更好地检测潜在效应也很重要。结果表明，在样本量和效应量较小的情况下不应使用显著性检验。在这些情况下应采用不同的方法。
