Skip to main content

ORIGINAL RESEARCH article

Front. Public Health
Sec. Infectious Diseases: Epidemiology and Prevention
Volume 13 - 2025 | doi: 10.3389/fpubh.2025.1546404
This article is part of the Research Topic Mapping the Unseen: Advancements and Innovations in Spatial Epidemiology for Disease Dynamics and Public Health Interventions View all articles

An extreme value analysis of daily new cases of COVID-19 in Africa

Provisionally accepted
Saralees Nadarajah Saralees Nadarajah 1,2*Adamu Abubakar Umar Adamu Abubakar Umar 2
  • 1 The University of Manchester, Manchester, United Kingdom
  • 2 Manchester University, North Manchester, Indiana, United States

The final, formatted version of the article will be published soon.

    Modeling COVID-19 cases in Africa is crucial for developing effective public health strategies, allocating resources efficiently, and mitigating the impact of the pandemic on vulnerable populations. A recent paper by the first author provided an extreme value analysis of daily new cases of COVID-19 from sixteen countries in west Africa. In this paper, we broaden our analysis to encompass data spanning all fifty four African nations over a period of forty four months. We identified extreme values as the monthly maximums of daily new cases. Utilizing the generalized extreme value distribution, we fitted the data, allowing two of its three parameters to vary linearly or quadratically in relation to the month number. Twenty six countries demonstrated significant downward trends in monthly maximums. Two countries demonstrated significant upward trends in monthly maximums. Nineteen countries demonstrated significant quadratic trends where monthly maximums initially increased before decreasing. The sharpest and weakest of the downward trends with respect to location were for Mali and Liberia, respectively. The sharpest and weakest of the downward trends with respect to scale were for Egypt and Libya, respectively. Recommendations are given for each country. We evaluated the adequacy of fits through probability plots and the Kolmogorov-Smirnov test. Subsequently, the fitted models were employed to determine quantiles of the monthly maximum of new cases, as well as their limits extrapolated to infinite month numbers.

    Keywords: Generalized extreme value distribution, Kolmogorov-smirnov test, linear trend, Quadratic trend, Estimation

    Received: 16 Dec 2024; Accepted: 13 Jan 2025.

    Copyright: © 2025 Nadarajah and Umar. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Saralees Nadarajah, The University of Manchester, Manchester, United Kingdom

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.