statsmodels.tsa.vector_ar.var_model.VARResults.forecast_cov

VARResults.forecast_cov(steps=1, method='mse')[source]

Compute forecast covariance matrices for desired number of steps

Parameters:
stepsint
Returns:
covsndarray (steps x k x k)

Notes

\[\Sigma_{\hat y}(h) = \Sigma_y(h) + \Omega(h) / T\]

Ref: Lütkepohl pp. 96-97