VECMResult._from_fit#

classmethod VECMResult._from_fit(fit, model)[source]#

Assemble the public result from the internal fit and its model.

Parameters:

  • fit (_VectorErrorCorrectionFit) – The packed reduced-rank fit.

  • model (_VectorErrorCorrectionModel[Self]) – The model that produced it, read for the sample, the labels, the order, the rank and the Johansen case.

Return type:

Self

Returns:

A populated result, with trend mapped from the Johansen case to the levels convention through _LEVELS_TREND.

Example

>>> import numpy as np
>>> rng = np.random.default_rng(0)
>>> common = np.cumsum(rng.standard_normal(200))
>>> y = np.column_stack([common, common + rng.standard_normal(200)])
>>> model = VECM(y, order=2, rank=1, cointegration_trend="restricted_constant")
>>> res = VECMResult._from_fit(model._fit_family(), model)
>>> res.cointegration_trend, res.trend, res.beta.shape
('restricted_constant', 'c', (3, 1))
On this page