statsmodels.tsa.vector_ar.var_model.VARResults.irf_errband_mc¶

VARResults.irf_errband_mc(orth=False, repl=1000, steps=10, signif=0.05, seed=None, burn=100, cum=False)[source]¶

Compute Monte Carlo integrated error bands assuming normally distributed for impulse response functions

Parameters:¶

orth : bool, default False¶

Compute orthogonalized impulse response error bands

repl : int¶

number of Monte Carlo replications to perform

steps : int, default 10¶

number of impulse response periods

signif : float (0 < signif <1)¶

Significance level for error bars, defaults to 95% CI

seed : int¶

np.random.seed for replications

burn : int¶

number of initial observations to discard for simulation

cum : bool, default False¶

produce cumulative irf error bands

Notes

Lütkepohl (2005) Appendix D

Return type:¶

Tuple of lower and upper arrays of ma_rep monte carlo standard errors