GVARResult.simulate

GVARResult.simulate(n=200, *, seed=None, burn=_SIMULATION_BURN)

A fresh sample path from the fitted system.

The estimated coefficients, deterministic terms, and innovation covariance generate burn + n periods from a zero start with Gaussian innovations; the first burn are discarded so the kept part is a draw from the stationary law when the system is stable. The deterministic time index runs 1 .. n over the kept part, so a trend model produces a sample a fit with the same trend would read as its own.

Parameters:

• n (int) – Observations kept.

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

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

Return type:

NDArray[double]

Returns:

An array of shape (n, k).

Raises:

SpecificationError – If the counts are not usable.