J4

• 数学 • 上一篇    下一篇

q对称熵损失函数下指数分布的参数估计

杜宇静1,2, 赖 民2   

  1. 1. 吉林特产高等专科学校基础部, 吉林 132109; 2. 吉林大学数学研究所, 长春 130012
  • 收稿日期:2004-03-18 修回日期:1900-01-01 出版日期:2005-01-26 发布日期:2005-01-20
  • 通讯作者: 杜宇静

Parameter Estimation of Exponential Distribution under q-Symmetric Entropy Loss Function

DU Yu-jing1,2, LAI Min2   

  1. 1. Department of Foundation, Jilin Local Speciality College, Jilin 132109, China; 2. Institute of Mathematics, Jilin University, Changchun 130012, China
  • Received:2004-03-18 Revised:1900-01-01 Online:2005-01-26 Published:2005-01-20
  • Contact: DU Yu-jing

摘要: 提出对称熵损失函数的一般形式(λ/δ)q+(δ/λ)q-2(q>0) , 即q对称熵损失. 讨论指数分布的尺度参数在此损失函数下的最小风险同变估计、 Bayes 估计和最小最大估计, 给出了更具一般性的结论, 并研究了(cT+d)-1形式 估计的可容许性和不可容许性.

关键词: Bayes估计, 同变估计, 最小最大估计, 尺度参数, 可容许性, q对称熵损失函数

Abstract: The present paper presents the general form of the symmetric entropy loss function, (λ/δ)q+(δ/λ)q-2(q>0), which is called the q-symmetric entropy loss function, and deals with the Byaesian estimation, the minimum risk equivalent estimation and the minimax estimation for the scale parameter of the exponential istribution under the loss function, the conclusion is generalized. The admissbility and inadmissibility of estimator with the form of (cT+d)-1 are discussed.

Key words: Bayesian estimation, equivalent estimation, minimax estimation, scale parameter, admissibility, q-symmetric entropy loss function

中图分类号: 

  • O212.5