ESTIMATING NORMAL MEANS WITH A CONJUGATE STYLE DIRICHLET PROCESS PRIOR
ESTIMATING NORMAL MEANS WITH A CONJUGATE STYLE DIRICHLET PROCESS PRIOR
复制标题
DOI：
10.1080/03610919408813196
复制
发表时间：
1994-01-01
影响因子：
0.9
通讯作者：
MACEACHERN, SN
中科院分区：
文献类型：
--
作者：
MACEACHERN, SN
估计许多正态均值的问题是通过分层模型来解决的。层次模型是标准共轭模型，但有一个例外：中间阶段的正态分布被具有正态形状的狄利克雷过程所取代。该模型的估计是通过吉布斯采样器的实现来完成的（参见 Escobar 和 West，1991）。本文介绍了一种在折叠状态空间上实现的新吉布斯采样器算法。获得了适用于一般设置的结果，表明状态空间的崩溃将提高吉布斯采样器的收敛速度。一个例子表明，所提出的状态空间崩溃可能会导致算法的显着改进。
The problem of estimating many normal means is approached by means of an hierarchical model. The hierarchical model is the standard conjugate model with one exception: the normal distribution at the middle stage is replaced by a Dirichlet process with a normal shape. Estimation for this model is accomplished through the implementation of the Gibbs sampler (see Escobar and West, 1991). This article describes a new Gibbs sampler algorithm that is implemented on a collapsed state space. Results that apply to a general setting are obtained, suggesting that a collapse of the state space will improve the rate of convergence of the Gibbs sampler. An example shows that the proposed collapse of the state space may result in a dramatically improved algorithm.