MarkovSwitchingARResult.simulate_regimes#

MarkovSwitchingARResult.simulate_regimes(n=200, *, seed=None, burn=_SIMULATION_BURN)[source]#

A fresh sample path together with the regimes that generated it.

Parameters:

  • n (int) – Observations kept.

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

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

Return type:

tuple[NDArray[double], NDArray[int_]]

Returns:

(y, regimes) of shapes (n,) and (n,), the regime labels 0 .. K - 1 in the order of intercepts.

Raises:

SpecificationError – If the counts are not usable.

Example

The simulated chain spends time in each regime at its ergodic frequency:

>>> import numpy as np
>>> rng = np.random.default_rng(0)
>>> p = np.array([[0.97, 0.03], [0.05, 0.95]])
>>> s = np.zeros(1500, dtype=int)
>>> for t in range(1, 1500):
...     s[t] = np.searchsorted(np.cumsum(p[s[t - 1]]), rng.random())
>>> y = np.array([-1.0, 1.5])[s] + 0.5 * rng.standard_normal(1500)
>>> res = MarkovSwitchingAR(y, order=1, n_regimes=2).fit(seed=0)
>>> path, regimes = res.simulate_regimes(5000, seed=1)
>>> shares = np.bincount(regimes, minlength=2) / 5000
>>> bool(np.allclose(shares, res.ergodic_prob, atol=0.05))
True