The Poisson Inverse Pareto Distribution and Its Application

Authors

  • Sirithip Wasinrat Faculty of Science, Chandrakasem Rajabhat University, Bangkok, Thailand
  • Boonyarit Choopradit Department of Mathematics and Statistics, Faculty of Science and Technology, Thammasat University, Pathumthani, Thailand

Keywords:

Unified model, long-term survival model, mixture distribution, value-at-risk, tail behavior

Abstract

This paper proposes a new combination of the inverse Pareto distribution as a three-parameter distribution—the Poisson inverse Pareto distribution—derived from the concept of a unified model for long-term survival analyses. This work derives the proposed distribution’s probability properties, including the survival, cumulative distribution, probability density, and hazard functions. Moreover, some properties of the Poisson inverse Pareto distribution are presented, such as the value-at-risk, tail behavior, quantile function, and order statistics. The maximum likelihood estimation is then studied to obtain a parameter estimation. This study’s simulation revealed that the estimated parameter’s mean-squared errors decreased when the sample size increased. Finally, this work illustrates the Poisson inverse Pareto distribution’s application using two real datasets to demonstrate that the proposed distribution provides a superior fit to that of other models.

Downloads

Download data is not yet available.

Downloads

Published

2022-12-29

How to Cite

Wasinrat, S. ., & Choopradit, B. . (2022). The Poisson Inverse Pareto Distribution and Its Application. Thailand Statistician, 21(1), 110–124. Retrieved from https://ph02.tci-thaijo.org/index.php/thaistat/article/view/248027

Issue

Section

Articles