Moment Matching Priors
Moment Matching Priors
复制标题
DOI：
10.1007/s13171-011-0012-2
复制
发表时间：
2011-08-01
影响因子：
0.7
通讯作者：
Liu, Ruitao
中科院分区：
文献类型：
--
作者：
Ghosh, Malay;Liu, Ruitao
在贝叶斯分析中，对于选择所谓的“客观”或“默认”先验，有各种各样的建议。本文提出了一种新的矩匹配准则，该准则要求后验均值与最大似然估计的匹配达到高阶逼近，并给出了单参数和多参数情况下这类先验的完整刻画。在这个过程中，产生了许多新的先验。一个有趣的发现是，即使在没有滋扰参数的情况下，也可能根据我们的标准找到不同于Jeffreys的实值参数先验的先验。AMS(2000)主题分类。初级62F15。
There are various proposals for the selection of the so-called "objective" or "default" priors in Bayesian analysis. The paper introduces a new criterion, the moment matching criterion, which requires the matching of the posterior mean with the maximum likelihood estimator up to a high order of approximation.A complete characterization of such priors in the one or multi-parameter case is provided. In the process, many new priors are derived. One interesting finding is that even in the absence of nuisance parameters, it is possible to find priors different from Jeffreys' prior for a real valued parameter based on our criterion.AMS (2000) subject classification. Primary 62F15.