Bayesian goodness-of-fit

被引:0
|
作者
Swartz, T
机构
关键词
Levy metric; Dirichlet process; Monte Carlo; hypothesis testing; non-parametric Bayesian inference;
D O I
暂无
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
This paper develops a systematic approach to Bayesian goodness-of-fit that parallels the ideas found in classical goodness-of-fit. An important feature of the approach is that we are able to test the practical scientific hypothesis of whether an underlying distribution is close to some hypothesized distribution. The notion of closeness requires the introduction of a metric for which we consider the Levy distance. Methodology is developed for both precise and composite hypotheses.
引用
收藏
页码:278 / 283
页数:6
相关论文
共 50 条