Academic Journal of Applied Mathematical Sciences
Online ISSN: 2415-2188
Print ISSN: 2415-5225
Print ISSN: 2415-5225
Quarterly Published (4 Issues Per Year)
![](https://arpgweb.com/images/crossref-and-g-scholar.png)
Archives
Volume 8 Number 3 July 2022
On Bivariate Modeling of the COVID-19 Data with a New Type I Half-Logistic Inverse Weibull Distribution
Authors: Ahmed Elhassanein
Pages: 42-68
DOI: doi.org/10.32861/ajams.83.42.68
Abstract
This manuscript presents a new univariate six parameters type I half-logistic inverse Weibull distribution. Explicit expressions for the quantile function, the moments, the moment generating function and the maximum likelihood esti-mators are formulated. Simulation is employed to investigate the goodness of fit and to discuss the behaviour of the new model. Competitive models are compared via real data. The univariate one is used as a base line to construct a bivariate one named bivariate six parameters type I half-logistic inverse Weibull distribution. Mathematical properties of the new bivariate distrib-ution are investigated. The goodness of fit and the model performance are discussed via simulation. COVID-19 mortality data for Italy and Canada are treated as a bivariate random variable to prove the applicability of the new bivariate distribution.