基于共轭正态分布的抽样检验方案  

Sampling inspection plans for conjugate normal distribution items

作　　者：魏鹏辉 秦桂香 梁小林 WEI Peng-hui;QIN Gui-xiang;LIANG Xiao-lin(School of Mathematics and Statistics,Changsha University of Technology,Changsha 410114,China)

机构地区：[1]长沙理工大学数学与统计学院,湖南长沙410114

出　　处：《湘潭大学学报（自然科学版）》2021年第4期13-17,34,共6页Journal of Xiangtan University(Natural Science Edition)

基　　金：湖南省大学生创新创业训练计划项目(S20201105360042)。

摘　　要：该文主要在双侧规格限下研究方差已知但均值未知的正态分布产品指标均值的抽样检验方案.首先利用共轭先验分布,得到产品指标均值的后验分布.然后根据指标均值检验统计量T的拒绝域以及生产和使用双方可承受的最大风险来确定检验的最大样本量.最后进行实例模拟,其结果表明,该文所确定的方法是可行的.In this paper,we investigate reliability sampling inspection method for items whose quality characteristic has a normal distribution with known variance but unknown mathematical expectation under double combined specification limits.Firstly,the posterior distribution of the mathematical expectation for product quality characteristic value is obtained by using conjugate prior distribution.Then,the maximum sample size of the hypothesis testing is obtained according to the rejection region of the testing statistic T about sample mean and the maximum risk which can be borne by producers and users.Finally,an example is simulated,and the results show that our method is reasonable.

关 键 词：正态分布 共轭先验分布 抽样检验 双侧规格限 

分 类 号：O212.8[理学—概率论与数理统计]