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
Hi, I'm dealing with a time series with an extreme outlier, and I've found the function outliers, that I imagine uses the IQR to determine if the observation is considered an outlier. However, there's no documentation about how to use it. Is this currently being developed?
The text was updated successfully, but these errors were encountered:
The outliers() functionality is mostly a stub at the moment, not many (any?) models support it yet, and so it is also not very well documented. You are correct that something like the IQR can be used, specifically we will default to using 1-step fitted values from the model. Further discussion is here: #314
Hi, I'm dealing with a time series with an extreme outlier, and I've found the function
outliers
, that I imagine uses the IQR to determine if the observation is considered an outlier. However, there's no documentation about how to use it. Is this currently being developed?The text was updated successfully, but these errors were encountered: