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
Scoringutils has an option for pairwise comparison that should work in this case because we are using them same set of forecast dates and locations (ww vs hosp)
mcs R package should also work and return the maximum set of distinguishable forecasts from the null hypothesis that all models perform the same (so could run this with the ARIMA + ww + hosp only)