A semi-parametric Bayesian approach to average bioequivalence
A semi-parametric Bayesian approach to average bioequivalence
复制标题
DOI：
10.1002/sim.2620
复制
发表时间：
2007-03-15
影响因子：
2
通讯作者：
Rosner, Gary L.
中科院分区：
文献类型：
--
作者：
Ghosh, Pulak;Rosner, Gary L.
生物等效性评价是一个备受关注的问题。发展评估生物等效性的统计方法是统计学家研究的一个重要领域。生物等效性通常根据正态分布确定。我们放宽了这一假设，并开发了一个半参数混合模型的生物等效性数据。该方法具有很强的灵活性和实际意义。我们提出的方法是基于混合正态分布和非参数贝叶斯方法，使用狄利克雷过程混合先验。一个数值例子说明了我们的方法的用法。版权所有(c) 2006约翰威利父子有限公司
Bioequivalence assessment is an issue of great interest. Development of statistical methods for assessing bioequivalence is an important area of research for statisticians. Bioequivalence is usually determined based on the normal distribution. We relax this assumption and develop a semi-parametric mixed model for bioequivalence data. The proposed method is quite flexible and practically meaningful. Our proposed method is based on a mixture normal distribution and a non-parametric Bayesian approach using a Dirichlet process mixture prior. A numerical example illustrates the use of our procedure. Copyright (c) 2006 John Wiley & Sons, Ltd.