截断删失数据下泊松分布参数的点估计

基金项目:

国家自然科学基金项目(61174099)

详细信息

Point Estimation of Parameter of Poisson Distribution for Truncated and Censored Data

1.
(1.School of Mathematics and Statistics,Anyang Normal University,Anyang 455000,China;
2.
2.School of Mathematics,Shandong University,Jinan 250100,China)

摘要: 利用EM算法和MCMC方法对截断删失数据下泊松分布寿命参数的点估计进行了研究.利用逆变换法和舍选法对缺损数据进行了填充,获得了产品的完全数据，得到了参数的EM迭代公式.对满条件分布进行了抽样,把Gibbs样本的算术平均值作为参数的MCMC估计.随机模拟的估计效果较好,估计值比较稳定,且精度较高.
- 截断删失数据 /
- 泊松分布 /
- 似然函数 /
- EM迭代公式 /
- MCEM方法
Abstract: The point estimation of parameter of Poisson distribution for truncated and censored data is studied by EM algorithm and MCMC method. The missing data is filled in and the complete data is obtained. The EM iterative formula of the parameter is given. After sampling from the full conditional distributions, Gibbs samples of the parameter are obtained, the mean of Gibbs samples is taken as MCMC estimation of the parameter. The random simulation results show that the effect of the estimation is good, and the estimation is relatively stable and precision is also higher.
- truncated and censored data /
- Poisson distribution /
- ikelihood function /
- EM iterative formula /
- MCEM method

1.	胡江山，隋云云，付云鹏. 左截断右删失数据中泊松分布的贝叶斯推断. 山东大学学报(理学版). 2021(07): 46-52 . 百度学术
2.	吴琴，刘寅，阮建. 广义泊松计数模型及其统计推断. 华南师范大学学报(自然科学版). 2019(06): 107-110 . 百度学术
3.	罗佳沩. 谨防点值估计中的推断错误. 才智. 2019(36): 34 . 百度学术