Sibling rivalry within inverse Weibull family to predict the COVID-19 spread in South Africa

ABSTRACT

This article draws attention to a comparative study of different members within the inverse Weibull Power Series (IWPS) to analyze the COVID-19 data from South Africa for the period from 27 March to 23 August 2020. A new sibling of the IWPS is introduced, namely the inverse Weibull negative binomial. An EM algorithm is developed for computing the maximum likelihood estimates of the model parameters. The IWPS growth curve model and its special cases are used for prediction of the COVID-19 spread in South Africa. It is found that the IWPS model fits the disease growth of the COVID-19 confirmed cases well with worthy long-term predictions. The IWPS growth curve modeling of South African predicts that the number of confirmed new cases will decrease at the end of November 2020.

KEYWORDS:

• Confirmed cases
• COVID-19
• growth curve
• IWPS
• prediction
• South African

Acknowledgments

The authors would like to thanks anonymous reviewers for their constructive comments with led to put many details in the paper. Opinions expressed and conclusions arrived at in this study are those of the authors and are not necessarily to be attributed to the NRF.

Additional information

Funding

This work was based upon research supported in part by the National Research Foundation (NRF) of South Africa, Reference: SRUG190308422768 grant No. 120839 and SARChI Research Chair UID: 71199, Re: IFR170227223754 grant No. 109214 and STATOMET.