Adds the level argument to MLForecast.forecast_fitted_values to add prediction intervals to the in-sample predictions. This is achieved by assuming the errors are normally distributed, computing their standard deviations by serie and using the appropriate quantile of the normal distribution to compute the widths.
Fixes #285
Checklist:
[x] This PR has a meaningful title and a clear description.
Description
Adds the
level
argument toMLForecast.forecast_fitted_values
to add prediction intervals to the in-sample predictions. This is achieved by assuming the errors are normally distributed, computing their standard deviations by serie and using the appropriate quantile of the normal distribution to compute the widths.Fixes #285
Checklist: