基于无失效数据指数分布参数的AMLE  

AMLE OF AN EXPONENTIAL PARAMETER BASED ON THE ZERO FAILURE DATA

作　　者：叶尔骅[1,2,3] 陈怡南[1,2,3] 华就昆 

机构地区：[1]南京航空航天大学 [2]连云港化工高等专科学校 [3]南京审计学院

出　　处：《高校应用数学学报（A辑）》1997年第2期183-190,共8页Applied Mathematics A Journal of Chinese Universities(Ser.A)

基　　金：航空科学基金

摘　　要：本文讨论了基于无失效数据指数分布参数的近似极大似然估计（ＡＭＬＥ）．利用Ｐｏｉｓｓｏｎ过程中年龄过程的多维生存分布的Ｌｅｂｅｓｇｕｅ分解式以及本文提出的伪样本估计法，导出了参数λ所满足的近似似然方程，讨论了解的存在唯一性．利用数值计算方法，最终可获得λ的ＡＭＬＥλｎ．大量随机模拟表明，其结果与真值很接近。This paper discusses the approximate maximum likelihood estimation (AMLE) of the parameter λ of the exponential lifetime distribution based on the zero failure data. With the aid of the Lebesgue decompositions of the n dimensional survival probability distribution functions of the age process in the Poisson process, and by the use of the quasi sample estimate method presented in this paper, we derive the approximate likelihood equation on the parameter λ, and discuss the existence and uniqueness of the solution of the equation. By numerical calculation, we may obtain AMLE  n of λ. The results of a lot of random simulation show that  n is more accurate and the rate of time saving is about 70%.

关 键 词：可靠性 无失效数据分析 指数分布 极大似然估计 

分 类 号：O213.2[理学—概率论与数理统计]