序约束下单向分类方差分析模型的Bayes变量选择

Bayesian Variable Selection in One-Way ClassifiedANOVA Models under Order Constraints

考虑序约束下单向分类方差分析模型的变量选择问题,提出两种基于SSVS的Bayes变量选择方法,并设计一种简单且易操作的Gibbs抽样算法进行后验抽样.数值模拟和应用实例结果表明,该方法效果较好.

We considered variable selection problem in one-way classified ANOVA under order constraints.We proposed two Bayesian variable selection method based on the stochastic search variable selection(SSVS),and designed a simple and easy to operate Gibbs sampling algorithm for a posteriors sampling.The results of numerical simulation and application examples show that the proposed method is effective.