独立二项分布序列变点的识别方法  

Identification Method of Independent Binary Distribution Sequence with Changepoints

作　　者：赵江南 庞冬 樊森德 ZHAO Jiang-nan;PANG Dong;FAN Sen-de(Mathematics and Physics College,Xinjiang Agricultural University,Urumqi 830052,China)

机构地区：[1]新疆农业大学数理学院

出　　处：《安徽师范大学学报（自然科学版）》2020年第1期6-10,共5页Journal of Anhui Normal University(Natural Science)

基　　金：新疆农业大学"大学生创新创业训练计划"项目,(201910758035)

摘　　要：运用IBF算法研究二项分布的变点问题,首先利用贝叶斯因子给出了识别变点个数的具体步骤,其次通过IBF算法给出了识别变点具体位置的步骤。并用软件进行了随机模拟,结果显示估计值较为精确。最后将本文推导的方法成功应用于两个实例,得到的结果与前人的一致。In this paper,the IBF algorithm is used to study the problem of the changepoints of the binary distribution.Firstly,the concrete steps of identifying the number of changepoints are given by using the Bayes factor,and then the concrete steps of identifying the specific locations of the changepoints points are given by the IBF algorithm.The software is used for random simulation,and the simulation results show that the estimated value is very accurate.Finally,the derivation method is applied to two examples successfully.

关 键 词：二项分布 变点 贝叶斯因子 IBF算法 

分 类 号：O212.8[理学—概率论与数理统计]