QVARResult.deterministic

QVARResult.deterministic(quantile)

One level’s deterministic coefficients, design-major.

Parameters:

quantile (float) – An estimated level.

Return type:

NDArray[double]

Returns:

An (n_det, k) block – column i belongs to equation i; empty when trend is "n".

Raises:

SpecificationError – If the level was not estimated.

Example

On symmetric innovations the intercepts order with the level:

>>> import numpy as np
>>> y = np.random.default_rng(0).standard_normal((300, 2))
>>> res = QVAR(y, order=1).fit(quantiles=(0.1, 0.5, 0.9))
>>> res.deterministic(0.5).shape
(1, 2)
>>> bool(np.all(res.deterministic(0.1) < res.deterministic(0.5)))
True
>>> bool(np.all(res.deterministic(0.5) < res.deterministic(0.9)))
True
>>> QVAR(y, order=1, trend="n").fit(quantiles=(0.5,)).deterministic(0.5).shape
(0, 2)