Aggregating Human Judgment Probabilistic Predictions of Coronavirus Disease 2019 Transmission, Burden, and Preventive Measures

Abstract

Aggregated human judgment forecasts for coronavirus disease 2019 (COVID-19) targets of public health importance are accurate, often outperforming computational models. Our work shows that aggregated human judgment forecasts for infectious agents are timely, accurate, and adaptable, and can be used as a tool to aid public health decision making during outbreaks.

Keywords: coronavirus disease 2019; forecasting; human judgment.

Figure 1.

Consensus median (black dot), 25th and 75th percentiles (bottom and top of solid black bar), and the 2.5th and 97.5th percentiles (bottom and top of rectangle) for predictive distributions of aggregate human judgment forecasts of weekly incident cases, hospitalizations, and deaths, cumulative first and full-dose vaccinations, and prevalence of immunity-evading variants at the United States national level. The number of weeks between when consensus predictions were generated to ground truth ranged from 1 to 3 weeks for the majority of predictions (see Supplementary Appendix B for more details). Predictions were submitted between January 2021 and June 2021. Predictions for survey 6 were made for the week starting on 27 June and ending on 3 July. The ground truth is a solid black line or a dashed black line. Rectangles are shaded using the viridis colormap with dark blue rectangles corresponding to low percentage error (PE) and bright yellow rectangles corresponding to high PE. Lighter rectangles correspond to higher PE.