Scholarlink

<p>A discrete analogue of the continuous power Teissier distribution is introduced by means of the survival discretization approach. Some statistical measures and properties are studied such as the moments, quantile function and hazard rate function, among others, and a Monte Carlo simulation study is conducted to verify that the maximum likelihood method provides satisfactory estimates of the model parameters. It is relevant to remark that the new distribution can handle both underdispersed and overdispersed count data and also that its hazard rate function can be increasing, decreasing and bathtub shaped. Therefore, the proposed distribution is flexible enough to model a wide variety of count data from different fields in practical applications, which is illustrated using several real data sets. Additionally, the first order integer-valued autoregressive process INAR(1) associated to the new discrete distribution is constructed and compared to other competing processes when time series of counts are considered.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

On the Discrete Power Teissier Distribution and the Associated INAR(1) Process

  • 期刊论文

  • 发表日期：

    2026年1月6日

查看全文
  • M. R. Irshad,
  • A. Krishna,
  • R. Maya,
  • P. Jodrá

摘要

A discrete analogue of the continuous power Teissier distribution is introduced by means of the survival discretization approach. Some statistical measures and properties are studied such as the moments, quantile function and hazard rate function, among others, and a Monte Carlo simulation study is conducted to verify that the maximum likelihood method provides satisfactory estimates of the model parameters. It is relevant to remark that the new distribution can handle both underdispersed and overdispersed count data and also that its hazard rate function can be increasing, decreasing and bathtub shaped. Therefore, the proposed distribution is flexible enough to model a wide variety of count data from different fields in practical applications, which is illustrated using several real data sets. Additionally, the first order integer-valued autoregressive process INAR(1) associated to the new discrete distribution is constructed and compared to other competing processes when time series of counts are considered.