VECMXResult._coefficient_stack#

VECMXResult._coefficient_stack()[source]#

Short-run coefficients, laid out exactly as the design columns.

Return type:

NDArray[double]

Returns:

A (width, k_y) array – deterministic terms, each lag’s transposed Gamma over the joint vector, the transposed impact block, then alpha.T.

Example

>>> import numpy as np
>>> rng = np.random.default_rng(0)
>>> x = np.cumsum(rng.standard_normal((200, 1)), axis=0)
>>> res = VECMX(x + rng.standard_normal((200, 1)), x, order=2, rank=1).fit()
>>> stack = res._coefficient_stack()
>>> stack.shape, bool(np.allclose(res.design @ stack, res.fittedvalues))
((5, 1), True)