Bayesian information in an experiment and the Fisher information distance

被引:18
|
作者
Walker, Stephen G. [1 ]
机构
[1] Univ Texas Austin, Dept Math, Austin, TX 78712 USA
关键词
Shannon entropy; Information; Bayesian design; DESIGNS;
D O I
10.1016/j.spl.2016.01.014
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
There are two forms of Fisher information; for the parameter of a model and for the information in a density model. These two forms are shown to be fundamentally connected through a measure of gain in information from a Bayesian experiment. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码:5 / 9
页数:5
相关论文
共 50 条