On families of distributions characterized by certain properties of ordered random variables


如何引用文章

全文:

开放存取 开放存取
受限制的访问 ##reader.subscriptionAccessGranted##
受限制的访问 订阅存取

详细

In this work, we obtain new characterizations of certain probability distributions by relations with different ordered random variables. Such variables include order statistics, sequential maxima, and records. We consider relations that include not only upper, but also lower record values. The presented ordered objects are based on sequences of independent random variables with a common continuous distribution function. We also investigate equalities in the distribution of sequential maxima exposed by various random shifts. These shifts (one-sided or two-sided) have exponential distributions. Certain theorems and their corollaries present corresponding characterizations of distributions by relations of such a type. In addition, we consider exponentially shifted order statistics such that simple relations among them also characterize certain probability distributions. All of the presented results yield a set of characterizations of various distributions. For particular cases, we present the relations that characterize families of classical exponential and logistic distributions.

作者简介

S. Ananjevskii

St. Petersburg State University

编辑信件的主要联系方式.
Email: ananjevskii@mail.ru
俄罗斯联邦, Universitetskaya nab. 7–9, St. Petersburg, 199034

V. Nevzorov

St. Petersburg State University

Email: ananjevskii@mail.ru
俄罗斯联邦, Universitetskaya nab. 7–9, St. Petersburg, 199034

补充文件

附件文件
动作
1. JATS XML

版权所有 © Allerton Press, Inc., 2016