摘要
研究了截断删失数据模型中线性指数分布的参数估计问题。分别利用极大似然估计法和EM算法对未知参数进行估计,并给出参数估计随机模拟检验,通过检验发现:极大似然估计得到的参数估计和EM算法得到的参数估计结果差不多,但是EM算法的收敛速度较快。
The parameter estimation of linear exponential distribution based on truncated and censored data model is studied.The maximum likelihood estimation method and EM algorithm are respectively used to estimate the unknown parameters,and stochastic simulations are carried out.It is found that the parameter estimation obtained by maximum likelihood estimation is similar to that ob-tained by EM algorithm,but the convergence speed of EM algorithm is faster.
作者
隋云云
胡江山
马树才
付云鹏
SUI Yun-yun;HU Jiang-shan;MA Shu-cai;FU Yun-peng(School of Mathematics and Information Science,Weifang University,Weifang 261061,Shandong,China;School of Eco-nomics,Liaoning University,Shenyang 110036,Liaoning,China)
出处
《山东大学学报（理学版）》
CAS
CSCD
北大核心
2020年第6期10-16,共7页
Journal of Shandong University(Natural Science)
基金
山东省社科规划资助项目(17CCXJ14)。
关键词
截断删失数据
线性指数分布
EM算法
truncated and censored data
linear exponential distribution
EM algorithm
