Bayes factors based on test statistics
Bayes factors based on test statistics
复制标题
DOI：
10.1111/j.1467-9868.2005.00521.x
复制
发表时间：
2005-01-01
影响因子：
5.8
通讯作者：
Johnson, VE
中科院分区：
文献类型：
--
作者：
Johnson, VE
传统上，贝叶斯因子的使用要求对模型参数的适当先验分布进行规范，这些参数对零假设和备选假设都是隐含的。我描述了一种基于建模检验统计来定义贝叶斯因子的方法。由于检验统计量的分布不依赖于未知的模型参数，这种方法消除了通常与贝叶斯因子定义相关的许多主观性。对于标准检验统计量，包括chi(2)-、F-、t-和z-统计量，这种方法得到的贝叶斯因子值具有简单的封闭形式表达式。
Traditionally, the use of Bayes factors has required the specification of proper prior distributions on model parameters that are implicit to both null and alternative hypotheses. I describe an approach to defining Bayes factors based on modelling test statistics. Because the distributions of test statistics do not depend on unknown model parameters, this approach eliminates much of the subjectivity that is normally associated with the definition of Bayes factors. For standard test statistics, including the chi(2)-, F-, t- and z-statistics, the values of Bayes factors that result from this approach have simple, closed form expressions.