statsmodels.tsa.vector_ar.var_model.VARProcess.long_run_effects VARProcess.long_run_effects() [source] Compute long-run effect of unit impulse

statsmodels.tsa.vector_ar.var_model.VARProcess.is_stable VARProcess.is_stable(verbose=False) [source] Determine stability based on model coefficients Parameters: verbose : bool Print eigenvalues of the VAR(1) companion Notes Checks if det(I - Az) = 0 for any mod(z) <= 1, so all the eigenvalues of the companion matrix must lie outside the unit circle

statsmodels.tsa.vector_ar.var_model.VARProcess.get_eq_index VARProcess.get_eq_index(name) [source] Return integer position of requested equation name

statsmodels.tsa.vector_ar.var_model.VARProcess.forecast_interval VARProcess.forecast_interval(y, steps, alpha=0.05) [source] Construct forecast interval estimates assuming the y are Gaussian Returns: (lower, mid, upper) : (ndarray, ndarray, ndarray) Notes Lutkepohl pp. 39-40

statsmodels.tsa.vector_ar.var_model.VARProcess.forecast_cov VARProcess.forecast_cov(steps) Compute theoretical forecast error variance matrices Parameters: steps : int Number of steps ahead Returns: forc_covs : ndarray (steps x neqs x neqs) Notes

statsmodels.tsa.vector_ar.var_model.VARProcess.forecast VARProcess.forecast(y, steps) [source] Produce linear minimum MSE forecasts for desired number of steps ahead, using prior values y Parameters: y : ndarray (p x k) steps : int Returns: forecasts : ndarray (steps x neqs) Notes Lutkepohl pp 37-38

statsmodels.tsa.vector_ar.var_model.VARProcess.acorr VARProcess.acorr(nlags=None) [source] Compute theoretical autocorrelation function Returns: acorr : ndarray (p x k x k)

statsmodels.tsa.vector_ar.var_model.VARProcess.acf VARProcess.acf(nlags=None) [source] Compute theoretical autocovariance function Returns: acf : ndarray (p x k x k)

statsmodels.tsa.varma_process.VarmaPoly.vstackarma_minus1 VarmaPoly.vstackarma_minus1() [source] stack ar and lagpolynomial vertically in 2d array

statsmodels.tsa.varma_process.VarmaPoly.vstack VarmaPoly.vstack(a=None, name='ar') [source] stack lagpolynomial vertically in 2d array