STARResult.simulate

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

A fresh sample path at the fitted parameters.

The transition variable is the series’ own delay-th lag, so the regime weight at each step is read from the simulated past through the fitted transition – a hard switch or the smooth function – and the two autoregressions are blended by it. burn initial periods from a zero start are discarded.

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,).

Raises:

SpecificationError – If the counts are not usable, or the transition variable is an external series whose future the result cannot know.