Three-Inflated Poisson Distribution and its Application in Suicide Cases of India During Covid-19 Pandemic

Tousifur Rahman; Partha Jyoti Hazarika; M Masoom Ali; Manash Pratim Barman

doi:10.1007/s40745-022-00372-1

Three-Inflated Poisson Distribution and its Application in Suicide Cases of India During Covid-19 Pandemic

Ann Data Sci. 2022;9(5):1103-1127. doi: 10.1007/s40745-022-00372-1. Epub 2022 Mar 15.

Authors

Tousifur Rahman¹, Partha Jyoti Hazarika¹, M Masoom Ali², Manash Pratim Barman¹

Affiliations

¹ Department of Statistics, Dibrugarh University, Dibrugarh, Assam 786004 India.
² Department of Mathematical Sciences, Ball State University, Muncie, IN 47306 USA.

Abstract

Inflated models are generally used whenever there is an excess number of frequencies at particular count. In this study, a three-inflated Poisson (ThIP) distribution is proposed by mixing the Poisson distribution and a distribution to a point mass at three. Some of its distribution properties and reliability characteristics are studied. A simulation study is carried out to see the performance of the MLEs. In India Covid-19 implications on mental health have been abysmal. Covid-19 related suicide data of India during lockdown to the first gradual relaxation of the terms of the total lockdown (unlocking 1.0) are used to examine the appropriateness of the proposed distribution. Likelihood ratio test is used for discriminating between Poisson and the proposed distribution.

Keywords: Covid-19; Health; Inflated; MLE; Three-inflated Poisson distribution.