几何分布中变点的贝叶斯分析  

Bayesian Analysis of Change Points in Geometric Distribution

作　　者：程贝丽 周菊玲[1] CHENG Bei-li;ZHOU Ju-ling(School of Mathematical Sciences,Xinjiang Normal University,Urumqi,Xinjiang,830017,China)

机构地区：[1]新疆师范大学数学科学学院,新疆乌鲁木齐830017

出　　处：《新疆师范大学学报（自然科学版）》2021年第2期1-5,共5页Journal of Xinjiang Normal University(Natural Sciences Edition)

基　　金：国家自然科学基金青年项目(11801488);新疆师范大学校级科研平台招标课题(XJNUSYS2019B05)。

摘　　要：文章首先利用二分分段法将几何分布多变点模型转化为单变点模型或无变点的模型,再将几何分布的变点问题转化为统计推断的问题,计算该模型的贝叶斯因子并得到未知参数的后验密度函数,利用MATLAB软件随机模拟,结果显示上述方法可以准确估计几何分布中变点的个数和位置。The article first uses the bisection method to transform the geometric distribution multi-change point model into a single-change-point model or a model with no change-point,and then transform the geometric distribution change-point problem into a statistical inference problem,and calculate the Bayesian of the model Fac-tor and obtain the posterior density function of unknown parameters,using Matlab software to simulate stochastically.The results show that the above method can effectively estimate the number and position of change points in the geo-metric distribution.

关 键 词：几何分布 变点 贝叶斯因子 二分分段法 

分 类 号：O212.1[理学—概率论与数理统计]