基于剩余寿命的寿命分布的几个新的偏序

基于剩余寿命函数,建立了利用寿命分布的几个新的偏序以度量年龄性质DMRL,NBUC,IFR(2),NBU(2)的程度,并讨论它们同已有的年龄性质的偏序之间的关系.     

平衡分布与寿命分布类

平衡分布给出了L分布类一个新的定义方式,并证明新定义与原定义等价.研究了平衡分布的一些性质,通过寿命的平衡分布与指数分布在Laplace变换下的比较,得到一种判定L(-L)类寿命分布的方法.进一步用平衡变量Xe的期望与寿命X的期望作比较提出一种新的寿命分布类--E类,研究了E类与其他寿命分布类之间的蕴含关系,证明了E类是比L类更大的一个分布类.最后讨论了E类在卷积下的封闭性质.     

以色散序新比旧好的寿命分布的一些性质

研究了基于色散序关系的新比旧好的寿命分布与NBU,DMRL寿命分布的关系,并得到了其关于串联结构的封闭性;最后讨论了该年龄性质在增凸函数作用下的不变性.     

A NEW CHARACTERIZATION OF NBU CLASS OF LIFE DISTRIBUTIONS WITH APPLICATION

Assume an unreliable workstation performing jobs with a random service time, namely, it occasionally breaks down because of unexpected interruptions. As an interruption really occurs, the station is instantaneously repaired and the uncompleted job is restarted again from the beginning till a job is completed without being interrupted. The total service time is shown to be NBU if and only if the total time it takes to finish each job with interruptions is stochastically larger than that without them, irrespective of when and how the breakdowns occur. As an application, a nonparametric procedure is developed to test for the strict NBU property of the service time. Finally, some numerical simulations are presented as well.     

记录值的一些偏序关系

证明了两个记录值序列依照凸序、星形序和超可加序排列当且仅当它们的基本分布分别依照凸序、星形序和超可加序排列.     

Upper Bounds for Ruin Probability with Stochastic Investment Return

Risk models with stochastic investment return are widely held in practice, as well as in more challenging research fields. Risk theory is mainly concerned with ruin probability, and a tight bound for ruin probability is the best for practical use. This paper presents a discrete time risk model with stochastic investment return. Conditional expectation properties and martingale inequalities are used to obtain both exponential and non-exponential upper bounds for the ruin probability.     

关于几个NBU寿命分布推广的一个注记

研究具有NBUC与NBU(2)到达间隔的更新过程的剩余寿命的行为，并给出了一个NBU，NBUC与NBU(2）关于卷积运算封闭性的统一证明．     

一种冲击源下冲击模型的寿命分布及其性质

考虑了一种特殊的冲击模型,系统受到强度为λ的Ｐｏｉｓｓｏｎ 流冲击,当冲击间隔小于给定常数δ时系统失效．根据首次冲击时间Ｘ１ ＜ δ引起失效或不引起失效建立模型Ⅰ,Ⅱ．对两个模型分别导出了系统寿命Ｔ的生存函数、均值、方差等,并研究了寿命分布的性质：模型Ⅰ中系统寿命分布属于ＮＷＵ分布类;模型Ⅱ中系统寿命分布属于ＮＢＵ分布类．还得到了Ｔ／ Ｅ（ Ｔ） 的渐近分布是参数为１ 的指数分布．     

NBU型寿命分布在不可靠服务中的特征

讨论了以寿命分布作为服务分布的服务系统中，系统不可靠和可靠两种情形下服务时间的分布性质，得出了系统不可靠时的服务时间随机大于系统可靠时的服务时间的充要条件为服务分布是ＮＢＵ型的。