Discussion of ‘Prior-based Bayesian Information Criterion (PBIC)’

作     者：Bertrand S.Clarke 

作者机构：Statistics DepartmentUniversity of Nebraska-Lincoln LincolnNEUSA 

出 版 物：《Statistical Theory and Related Fields》 (统计理论及其应用（英文）)

年 卷 期：2019年第3卷第1期

页      面：26-29页

学科分类：07[理学] 0714[理学-统计学（可授理学、经济学学位）] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 070101[理学-基础数学] 

主　　题：estimation. Criterion parameter 

摘      要：*** The authors have the basis for a reformulation of the BIC as we think of it *** problem is both hard and *** particular,to address it,the authors have put six incisive ideas in *** first is the separation of parameters that are common across models versus those that aren’*** second is the use of an orthogonal(why not orthonormal?)transformation of the Fisher information matrix to get diagonal entries di that summarise the parameter-by-parameter efficiency of *** third is using Laplace’s method only on the likelihood,i.e.