Evaluating short-term forecasting of COVID-19 cases among different epidemiological models under a Bayesian framework

Abstract

Background: Forecasting of COVID-19 cases daily and weekly has been one of the challenges posed to governments and the health sector globally. To facilitate informed public health decisions, the concerned parties rely on short-term daily projections generated via predictive modeling. We calibrate stochastic variants of growth models and the standard susceptible-infectious-removed model into 1 Bayesian framework to evaluate and compare their short-term forecasts.

Results: We implement rolling-origin cross-validation to compare the short-term forecasting performance of the stochastic epidemiological models and an autoregressive moving average model across 20 countries that had the most confirmed COVID-19 cases as of August 22, 2020.

Conclusion: None of the models proved to be a gold standard across all regions, while all outperformed the autoregressive moving average model in terms of the accuracy of forecast and interpretability.

Keywords: COVID-19; SARS-CoV-2; stochastic SIR model; stochastic growth model; time-series cross-validation.