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
Currently, in the recovery diagnostic plot, the uncertainty of the posteriors (shown via error bars) is computed using the MAD through the uncertainty_agg argument. This can be misleading, particularly when dealing with asymmetric posterior distributions.
A more informative approach would be to allow error bars to represent credible intervals (e.g., 90% or 95%). This would capture asymmetry in the posteriors more accurately and provide a clearer picture of the underlying uncertainty.