A tolerance interval approach for assessment of agreement in method comparison studies with repeated measurements
A tolerance interval approach for assessment of agreement in method comparison studies with repeated measurements
复制标题
DOI：
10.1016/j.jspi.2007.03.056
复制
发表时间：
2008-04-01
影响因子：
0.9
通讯作者：
Choudhary, Pankaj K.
中科院分区：
文献类型：
--
作者：
Choudhary, Pankaj K.
本文推广了容许区间方法，用于评估重复测量数据的两种连续测量方法之间的一致性，这是应用中的一种常见情况。重复测量可以是纵向的，或者它们可以是相同基础测量的复制。我们的方法是首先使用混合模型对数据进行建模，然后为适当定义的差异的分布构建相关的渐近容许区间（或带）。我们提出的方法在一般情况下的混合模型，可以将协变量，异方差和序列相关的错误。无协变量的情况下，模拟表明所提出的方法具有良好的小样本性能。对于纵向数据，我们还描述了一个扩展的情况下，观察到的时间曲线通过惩罚样条非参数建模。两个真实的数据应用。(C)2007 Elsevier B.V.保留所有权利。
This paper generalizes the tolerance interval approach for assessing agreement between two methods of continuous measurement for repeated measurement data-a common scenario in applications. The repeated measurements may be longitudinal or they may be replicates of the same underlying measurement. Our approach is to first model the data using a mixed model and then construct a relevant asymptotic tolerance interval (or band) for the distribution of appropriately defined differences. We present the methodology in the general context of a mixed model that can incorporate covariates, heteroscedasticity and serial correlation in the errors. Simulation for the no-covariate case shows good small-sample performance of the proposed methodology. For the longitudinal data, we also describe an extension for the case when the observed time profiles are modelled nonparametrically through penalized splines. Two real data applications are presented. (C) 2007 Elsevier B.V. All rights reserved.