Fitting COVID-19 datasets to a new statistical model

Abstract

This paper discussed gull alpha power Weibull distribution with a three-parameter. Different statistical inference methods of Gull Alpha Power Weibull distribution parameters have been obtained, estimated, and evaluated. Then, the results are compared to find a suitable model. The unknown parameters of the published Gull Alpha Power Weibull distribution are analyzed. Seven estimation methods are maximum likelihood, Anderson–Darling, right-tail Anderson–Darling, Cramér–von Mises, ordinary least-squares, weighted least-squares, and maximum product of spacing. In addition, the performance of this distribution is computed using the Monte Carlo method, and the limited sample features of parameter estimates for the proposed distribution are analyzed. In light of the importance of heavy-tailed distributions, actuarial approaches are employed. Applying actuarial criteria such as value at risk and tail value at risk to the suggested distribution shows that the model under study has a larger tail than the Weibull distribution. Two real-world COVID-19 infection datasets are used to evaluate the distribution. We analyze the existence and uniqueness of the log-probability roots to establish that they represent the global maximum. We conclude by summarizing the outcomes reported in this study.