Sebastian Funk

This PR is meant to supersede #213 and #214. It - finalises the work commenced in #214 to support [three different models](https://github.com/epiforecasts/EpiNow2/pull/214#issuecomment-753024893) - merges #214 into #213 and implements most...

add more flexibility with delays

4

This adds support for - fixed delays (mean only), or fixed delay distributions (mean + sd) - fixed truncation distributions (mean + sd) as well as unit tests for these....

option for secondary baseline

5

Adds a baseline level to the secondary model, i.e. a constant component that is not affected by the primary data stream (somewhat akin to the endemic component in `hhh4`. This...

start on static delays

1

Picks out the new features in https://github.com/epiforecasts/EpiNow2/pull/308 relating to static delays. Creating this as draft PR as it seems unfinished.

Picks out the new features in #308 relating to the secondary model.

Fit to multiple time series and fold in secondary model

1

It might be nice to add functionality to have multiple observation time series assuming that they are all reported from the same infection proces with a delay and scale. This...

Update R6 list definition to only require setting any defaults once.

2

None of the national estimates has been produced for three days. Is there a log somewhere that would flag this up and report the error?

Fixes to allow looking at BA.2 vs BA.1

2

+ results

add options for limiting/expanding plot limits

16

This is a somewhat clunky proposal to add the ability to zoom in (and limit to 0) to plots with balooning predictive uncertainty, such as in https://covid19forecasthub.eu/reports/ensemble-report-2021-03-29.html

plot_predictions: connect to last data point?

12

Would it make sense to change plot_predictions so that it connects to day on which the forecast was made? This is the way it is done in the forecast hub...