Tse S K, Chow S C
Department of Applied Statistics and Operational Research, City University of Hong Kong, Hong Kong.
J Biopharm Stat. 1995 Nov;5(3):285-96. doi: 10.1080/10543409508835114.
This paper discusses the selection of an appropriate statistical model for representing standard curve in assay development. This is an important issue in assay validation because the accuracy and reliability of the assay result depend on the selected standard curve. In this study, we propose a selection procedure, which is based on the R2 and the mean squared error of the estimation sample, to determine the "best" model. An example concerning an assay validation study is used to illustrate the application of the proposed procedure to discriminate among the five commonly used statistical models.
本文讨论了在分析方法开发中选择合适的统计模型来表示标准曲线的问题。这是分析方法验证中的一个重要问题，因为分析结果的准确性和可靠性取决于所选的标准曲线。在本研究中，我们提出了一种基于R2和估计样本的均方误差的选择程序，以确定“最佳”模型。通过一个关于分析方法验证研究的例子来说明所提出的程序在区分五种常用统计模型中的应用。
