Hertzog C, Rovine M
Child Dev. 1985 Aug;56(4):787-809.
This paper presents a review of recent developments in statistical techniques for repeated-measures analysis of variance. Since the literature has emphasized the issue of mixed model assumptions and their violation, we present an updated perspective on the nature of these assumptions and their implications for mixed model, adjusted mixed model, or multivariate significance tests. However, the central theme of the review is that the validity of mixed model assumptions is but one consideration in selection of an appropriate method of repeated-measures ANOVA. In particular, we recommend the avoidance of omnibus significance tests in favor of specific planned comparisons whenever hypotheses more specific than the omnibus null hypothesis may be formulated a priori. The analyst must also consider whether multiple dependent measures are to be analyzed, and the paper discusses alternative approaches to true multivariate repeated-measures designs. It also includes discussion of other relevant issues, including a brief review of the strengths and weaknesses of commonly available statistical software when applied to the analysis of repeated-measures data.
本文综述了重复测量方差分析统计技术的最新进展。由于文献强调了混合模型假设及其违背的问题，我们对这些假设的性质及其对混合模型、调整混合模型或多变量显著性检验的影响提出了一个更新的观点。然而，综述的核心主题是，混合模型假设的有效性只是选择合适的重复测量方差分析方法时要考虑的一个因素。特别是，我们建议避免进行综合显著性检验，而应在能够事先制定比综合零假设更具体的假设时，采用特定的计划比较。分析人员还必须考虑是否要分析多个相关测量，本文讨论了真正多变量重复测量设计的替代方法。它还包括对其他相关问题的讨论，包括简要回顾常用统计软件在应用于重复测量数据分析时的优缺点。
