Evaluating real-world forecasts
Nowcasting and forecasting of infectious disease dynamics
Hubs accelerate scientific discovery
“Comparing the accuracy of forecasting applications is difficult because forecasting methods, forecast outcomes, and reported validation metrics varied widely.”
– Chretien et al., PLOS ONE, 2014
Launched April 2020 by the Reich Lab in collaboration with CDC. Goals were to:
Provide decision-makers and general public with reliable information about where the pandemic is headed in the next month.
Assess reliability of forecasts and gain insight into which modeling approaches do well.
Create a community of infectious disease modelers underpinned by an open-science ethos.
…provided CDC with weekly forecasts
…had prominent uses
What does hubverse data look like?
Some columns define a prediction task
Others are always present
Why is standardization important?
You will learn by doing in this session.
From a practical standpoint, standards facilitate
visualization
evaluation
ensembling
COVID Hub reboot (2024-present)
In 2024, CDC rebooted the hub, using hubverse standards.
These are the data that you will use in this session.
Your Turn
Use COVID-19 Forecast Hub forecasts to …
create forecast visualizations.
evaluate multiple forecast models.
create weighted ensembles.