ssfortran.ForecastResults#
- class ssfortran.ForecastResults(predicted_mean, var_pred_mean)#
Forecasts past the end of the sample (DK §4.11).
- Attributes:
- predicted_meanndarray, shape (steps,) or (steps, p)
\(E(y_{n+j} | Y_n)\); one column per series.
- var_pred_meanndarray, shape (steps, p, p)
\(Var(y_{n+j} | Y_n)\).
- conf_int(alpha=0.05)#
Compute pointwise normal confidence intervals.
- Parameters:
- alphafloat, optional
One minus the coverage.
- Returns:
- lower, upperndarray
Bounds, shaped as predicted_mean.
- property se_mean#
Standard errors of the forecasts, shaped as predicted_mean.