Ray, Evan L; Brooks, Logan C; Bien, Jacob; Biggerstaff, Matthew; Bosse, Nikos I; Bracher, Johannes; Cramer, Estee Y; Funk, Sebastian; Gerding, Aaron; Johansson, Michael A; +5 more... Rumack, Aaron; Wang, Yijin; Zorn, Martha; Tibshirani, Ryan J; Reich, Nicholas G; (2022) Comparing trained and untrained probabilistic ensemble forecasts of COVID-19 cases and deaths in the United States. International Journal of Forecasting, 39 (3). pp. 1366-1383. ISSN 0169-2070 DOI: https://doi.org/10.1016/j.ijforecast.2022.06.005
Permanent Identifier
Use this Digital Object Identifier when citing or linking to this resource.
Abstract
The U.S. COVID-19 Forecast Hub aggregates forecasts of the short-term burden of COVID-19 in the United States from many contributing teams. We study methods for building an ensemble that combines forecasts from these teams. These experiments have informed the ensemble methods used by the Hub. To be most useful to policymakers, ensemble forecasts must have stable performance in the presence of two key characteristics of the component forecasts: (1) occasional misalignment with the reported data, and (2) instability in the relative performance of component forecasters over time. Our results indicate that in the presence of these challenges, an untrained and robust approach to ensembling using an equally weighted median of all component forecasts is a good choice to support public health decision-makers. In settings where some contributing forecasters have a stable record of good performance, trained ensembles that give those forecasters higher weight can also be helpful.
Item Type | Article |
---|---|
Faculty and Department | Faculty of Epidemiology and Population Health > Dept of Infectious Disease Epidemiology & Dynamics (2023-) |
Research Centre |
Covid-19 Research Centre for the Mathematical Modelling of Infectious Diseases |
PubMed ID | 35791416 |
Elements ID | 181184 |
Download
Filename: Ray_etal_2022_Comparing-trained-and-untrained-probabilistic.pdf
Description: This is an author accepted manuscript version of an article accepted for publication, and following peer review. Please be aware that minor differences may exist between this version and the final version if you wish to cite from it.
Licence: Creative Commons: Attribution 4.0
Download