A Time Series Approach to Assess the Impact of the COVID-19 Pandemic on the South African Tourism Sector

Abstract

The chapter examines tourism flows all over the world with a special case of all foreign tourists to South Africa (SA) from January 2009 to December 2023. A time series approach is used, and the model obtained is used to forecast and evaluate the effects of COVID-19 on total tourist arrivals in SA. The model forecasts are used in comparison with actual tourist arrivals after February 2020 when COVID-19 restrictions were employed. Monthly data on arrivals of all tourists to SA was considered. The ARIMA (0,1,1)(0,1,1)12 model was obtained considering its lowest value of the Bayesian Information Criterion (BIC) through the Box and Jenkins methodology. The forecasting power of the model is evidenced by its Mean Absolute Percentage Error (MAPE) of 1.934579. The effects of COVID-19 are realized form the difference in forecasts made and actual figures recorded from March 2020 when COVID-19 restrictions were effected. This study gives an overview of the contribution being realized from tourism receipts through an analysis of tourist arrivals before, during and after the COVID-19 pandemic. This helps inform various tourism stakeholders on how best the tourism sector may be revived through informative forecasts, good planning and policy formulation strategies.