A new versatile modification of the Rayleigh distribution for modeling COVID-19 mortality rates

Mutua Kilai; Gichuhi A Waititu; Wanjoya A Kibira; M M Abd El-Raouf; Tahani A Abushal

doi:10.1016/j.rinp.2022.105260

A new versatile modification of the Rayleigh distribution for modeling COVID-19 mortality rates

Results Phys. 2022 Apr:35:105260. doi: 10.1016/j.rinp.2022.105260. Epub 2022 Feb 22.

Authors

Mutua Kilai¹, Gichuhi A Waititu², Wanjoya A Kibira², M M Abd El-Raouf³, Tahani A Abushal⁴

Affiliations

¹ Department of Mathematics, Pan African Insitute of Basic Science, Technology and Innovation, Nairobi, Kenya.
² Department of Statistics and Actuarial Sciences, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya.
³ Basic and Applied Science Institute Arab Academy for Science, Technology and Maritime Transport (AASTMT), Alexandria, Egypt.
⁴ Department of Mathematical Science, Faculty of Applied Science, Umm Al-Qura University, Saudi Arabia.

Abstract

The aim of this paper is to specify a new flexible statistical model to analyze COVID-19 mortality rates in Italy and Canada. A new versatile lifetime distribution with four parameters is proposed by using the exponentiated generalized class of distributions and the gull alpha power Rayleigh distribution to form the exponentiated generalized gull alpha power Rayleigh (EGGAPR) distribution. This new distribution is characterized by a tractable cumulative distribution function. To estimate the unknown parameters of the proposed distribution the maximum likelihood estimation method is used. In evaluating the effectiveness of the MLE method graphical displays of the Monte Carlo simulation are presented. The EGGAPR distribution is compared to its sub-models which include the exponentiated gull alpha Rayleigh distribution, the gull alpha Rayleigh distribution, exponentiated generalized Rayleigh distribution, exponentiated Rayleigh distribution and the Rayleigh distribution. Different measures of goodness-of-fit are used to investigate whether the EGGAPR distribution is more flexible and fit than its sub-models in modeling COVID-19 mortality rates.

Keywords: COVID-19; Exponentiated generalized gull alpha power family; Rayleigh distribution.