BVARSVResult.simulate#

BVARSVResult.simulate(n=200, *, seed=None, burn=_SIMULATION_BURN, draw=None)[source]#

A fresh sample path from the fitted system at the posterior mean or at one draw.

burn + n periods are generated from a zero start and the first burn discarded; the deterministic time index runs 1 .. n over the kept part. At the posterior mean the path is a draw from the model’s law at a point estimate; at a retained draw it is a draw from the posterior predictive of a fresh sample, and looping over draws gives that predictive in full.

Parameters:

  • n (int) – Observations kept.

  • seed (int | Generator | None) – Seed or generator.

  • burn (int) – Periods discarded from the start.

  • draw (int | None) – Index of a retained draw, or None for the posterior mean.

Return type:

NDArray[double]

Returns:

An array of shape (n, k).

Raises:

SpecificationError – If the counts are not usable or the draw index is out of range.