随机删失数据下基于EM算法的Weibull分布参数估计  

Parameter Estimation of Weibull Distribution Using the EM Algorithm Based on Randomly Censored Data

作　　者：吴耀国[1] 周杰[1] 王柱[1] 曾艳[1] 

机构地区：[1]四川大学数学学院,成都610064

出　　处：《四川大学学报（自然科学版）》2005年第5期910-913,共4页Journal of Sichuan University(Natural Science Edition)

摘　　要：生存分析中的观测数据具有样本小、数据随机删失的特点.而目前处理这类问题所使用的参数估计方法并不理想.作者基于EM算法给出随机删失数据下Weibull分布的参数估计方法,证明了估计量满足一个非线性方程组,并用实例表明了此方法的有效性.Measuring data in survival analysis always runs to the problem of small sample and data being randomly censored, while the method for dealing with this kind of problem is often unsatisfactory. The authors propose a parameter estimation method of Weibull distribution using the EM algorithm based on randomly censored data, and prove that the estimators satisfy a system of non-linear equations. The experimental results show that the presented approach is accurate and efficient.

关 键 词：参数估计 EM算法 删失数据 WEIBULL分布 

分 类 号：O212.1[理学—概率论与数理统计]