You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
As discussed f2f it is useful to have baseline models to compare pyrenew out-of-sample forecast skill.
As pyrenew-he is in active dev @damonbayer@dylanhmorris, I'm proposing constructing a vector ARIMA (VARIMA) model to run on NHSN jointly with ED visits. I think there are a two configurations that are worth trying:
For target pathogen (Flu/Covid/RSV) we joint forecast on NHSN and ED visits for that target.
For target pathogen (Flu/Covid/RSV) we joint forecast on NHSN and ED visits for all targets. The hypothesis here would be that autocorrelations with other targets might aid forecast skill.
I'm proposing to follow other time series baselines and use fable to construct the model and perform parameter optimisation.
The text was updated successfully, but these errors were encountered:
As discussed f2f it is useful to have baseline models to compare
pyrenew
out-of-sample forecast skill.As
pyrenew-he
is in active dev @damonbayer @dylanhmorris, I'm proposing constructing a vector ARIMA (VARIMA) model to run on NHSN jointly with ED visits. I think there are a two configurations that are worth trying:RSV) we joint forecast on NHSN and ED visits for that target.RSV) we joint forecast on NHSN and ED visits for all targets. The hypothesis here would be that autocorrelations with other targets might aid forecast skill.I'm proposing to follow other time series baselines and use
fable
to construct the model and perform parameter optimisation.The text was updated successfully, but these errors were encountered: