Modelling COVID-19 incidence in the African sub-region using smooth transition autoregressive model

Eric N. Aidoo*, Richard T. Ampofo, Gaston E. Awashie, Simon K. Appiah, Atinuke O. Adebanji

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)


Prediction of COVID-19 incidence and transmissibility rates are essential to inform disease control policy and allocation of limited resources (especially to hotspots), and also to prepare towards healthcare facilities demand. This study demonstrates the capabilities of nonlinear smooth transition autoregressive (STAR) model for improved forecasting of COVID-19 incidence in the Africa sub-region were investigated. Data used in the study were daily confirmed new cases of COVID-19 from February 25 to August 31, 2020. The results from the study showed the nonlinear STAR-type model with logistic transition function aptly captured the nonlinear dynamics in the data and provided a better fit for the data than the linear model. The nonlinear STAR-type model further outperformed the linear autoregressive model for predicting both in-sample and out-of-sample incidence.

Original languageEnglish
Pages (from-to)961-966
Number of pages6
JournalModeling Earth Systems and Environment
Early online date26 Feb 2021
Publication statusPublished - Mar 2022


  • Africa
  • COVID-19
  • Nonlinearity
  • Regime switching
  • Smooth transition
  • STAR model

ASJC Scopus subject areas

  • Environmental Science(all)
  • Agricultural and Biological Sciences(all)
  • Statistics, Probability and Uncertainty
  • Computers in Earth Sciences

Cite this