左截断右删失数据下指数分布参数多变点的贝叶斯估计  

On Bayesian Estimation of Parameter of Exponential Distribution with Multiple Change Points for Randomly Truncated and Censored Data

作　　者：何朝兵[1] 刘跃军[2] 刘华文[3] 

机构地区：[1]安阳师范学院数学与统计学院,河南安阳455000 [2]安阳师范学院软件学院,河南安阳455000 [3]山东大学数学学院,济南250100

出　　处：《西南师范大学学报（自然科学版）》2015年第1期12-17,共6页Journal of Southwest China Normal University(Natural Science Edition)

基　　金：国家自然科学基金项目(61174099);河南省教育厅科学技术研究重点项目(12A520001)

摘　　要：主要利用MCMC方法研究了左截断右删失数据下指数分布多变点模型的参数估计问题.通过筛选法和逆变换法得到了指数分布的完全数据,在获得各参数的满条件分布后,利用MCMC方法得到了Gibbs样本,把Gibbs样本的均值作为各参数的估计.随机模拟的结果表明各参数估计的精度都较高.Parameter estimation in exponential distribution multiple change points model for randomly truncated and censored data has been studied in this paper.The complete data of exponential distribution has been obtained by screening method and inverse transformation method.After the full conditional distributions of all parameters have been obtained,Gibbs samples have been obtained in MCMC method,and the means of Gibbs samples has been taken as Bayesian estimations of the parameters.Random simulation results show that Bayesian estimations of the parameters are fairly accurate.

关 键 词：完全数据似然函数 满条件分布 MCMC方法 GIBBS抽样 Metropolis-Hastings算法 

分 类 号：O213.2[理学—概率论与数理统计] O212.8[理学—数学]