Power analyses for longitudinal trials and other clustered designs
Power analyses for longitudinal trials and other clustered designs
复制标题
DOI：
10.1002/sim.1869
复制
发表时间：
2004-09-30
影响因子：
2
通讯作者：
Crits-Christoph, P
中科院分区：
文献类型：
--
作者：
Tu, XM;Kowalski, J;Crits-Christoph, P
现有的纵向和其他聚类研究设计的功效和样本量估计方法应用有限。在本文中，我们回顾和扩展现有的方法来改善这些限制。特别是，我们专注于功率分析的两个最流行的方法，聚类数据分析，广义估计方程和线性混合效应模型。通过基于模型估计值的渐近分布推导幂函数，所提出的方法提供了与数据分析的推断方法一致的幂估计值。所提出的方法与众多的例子，是出于真实的研究设计。版权所有（C）2004约翰威利父子有限公司。
Existing methods for power and sample size estimation for longitudinal and other clustered study designs have limited applications. In this paper, we review and extend existing approaches to improve these limitations. In particular, we focus on power analysis for the two most popular approaches for clustered data analysis, the generalized estimating equations and the linear mixed-effects models. By basing the derivation of the power function on the asymptotic distribution of the model estimates, the proposed approach provides estimates of power that are consistent with the methods of inference for data analysis. The proposed methodology is illustrated with numerous examples that are motivated by real study designs. Copyright (C) 2004 John Wiley Sons, Ltd.