Evaluating epidemic forecasts in an interval format

• Published in: PLoS computational biology Vol. 17; no. 2; p. e1008618
• Main Authors: Bracher, Johannes, Ray, Evan L, Gneiting, Tilmann, Reich, Nicholas G
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 01.02.2021; Public Library of Science (PLoS)
• Subjects: Communicable Diseases - epidemiology; Coronaviruses; COVID-19; COVID-19 - epidemiology; COVID-19 - virology; Data collection; Decision analysis; Disease control; Epidemics; Epidemiology; Fines & penalties; Forecasting; Hospitalization; Humans; Infectious diseases; Medicine and Health Sciences; Pandemics; People and places; Physical Sciences; Probability; Public health; Research and Analysis Methods; SARS-CoV-2 - isolation & purification; Situational awareness; United States > US
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1008618

For practical reasons, many forecasts of case, hospitalization, and death counts in the context of the current Coronavirus Disease 2019 (COVID-19) pandemic are issued in the form of central predictive intervals at various levels. This is also the case for the forecasts collected in the COVID-19 Forecast Hub (https://covid19forecasthub.org/). Forecast evaluation metrics like the logarithmic score, which has been applied in several infectious disease forecasting challenges, are then not available as they require full predictive distributions. This article provides an overview of how established methods for the evaluation of quantile and interval forecasts can be applied to epidemic forecasts in this format. Specifically, we discuss the computation and interpretation of the weighted interval score, which is a proper score that approximates the continuous ranked probability score. It can be interpreted as a generalization of the absolute error to probabilistic forecasts and allows for a decomposition into a measure of sharpness and penalties for over- and underprediction.