Introduction to nowcasting

Nowcasting and forecasting of infectious disease dynamics

Often we see data like this

Data after the dashed line are marked as uncertain. What, if anything, do they tell us about current trends?

… or like this

… or like this

These patterns arise because:

Epidemiological time series are aggregated by the epidemiologically meaningful date (e.g. symptom onset, hospital admission, death)
There is a delay between this date, and the events showing up in the data
This leads to an “articifial” dip in the most recent data

Predict what an epidemiological time series will look like after all delayed reports are in.

(slide courtesy of Johannes Bracher)

Right truncation

reporting of events can be triggered by the secondary event
in that case, longer delays might be missing because whilst the primary events have occurred the secondary events have not occurred yet

Nowcasting is exactly this!.

Estimate the delay distribution from other data
Specify a model for the epidemic dynamics
Use the estimated delay distribution to model the expected right truncation in the data
Fit the model to the truncated data
Use the untruncated estimates from the model as the nowcast

Your Turn