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
When a model is fitted, its endog_index_ attribute becomes available as a DatetimeIndex containing the indexes for all the observations upon which the model was trained. However, when this model is then updated with new observations, even though its other attributes will update (for example, arparams() will return updated values), endog_index_ will still only have the original indexes upon which the model that was trained, and none of the indexes of the new data upon which update() was called.
Is this the intended behavior? If not, I will create a bug report.
Versions (if necessary)
No response
The text was updated successfully, but these errors were encountered:
Describe the question you have
When a model is fitted, its endog_index_ attribute becomes available as a DatetimeIndex containing the indexes for all the observations upon which the model was trained. However, when this model is then updated with new observations, even though its other attributes will update (for example, arparams() will return updated values), endog_index_ will still only have the original indexes upon which the model that was trained, and none of the indexes of the new data upon which update() was called.
Is this the intended behavior? If not, I will create a bug report.
Versions (if necessary)
No response
The text was updated successfully, but these errors were encountered: