VECMResult._summary_table#

VECMResult._summary_table()[source]#

Build the structured summary.

The coefficient rows are the short-run regression with its inference columns; below them the cointegrating vectors on the normalized_beta() basis, one row per variable and per restricted term, with the inference columns blank because beta carries no standard errors here. The notes state the common-trend count, the conditioning on beta, the identification of the space rather than the vector, the mismatch between the printed ec loadings and the printed basis, and the Cholesky ordering; an explosive root is flagged first.

Return type:

SummaryTable

Returns:

The SummaryTable behind summary().

Example

>>> import numpy as np
>>> rng = np.random.default_rng(0)
>>> common = np.cumsum(rng.standard_normal(300))
>>> y = np.column_stack([common, 2 * common + rng.standard_normal(300)])
>>> table = VECM(y, order=2, rank=1).fit()._summary_table()
>>> table.title, dict(table.metadata)["Common trends"]
('VECM(2) Results', '1')
>>> [row[0] for row in table.rows[-3:]]
['y2: ec1', 'beta[1]: y1', 'beta[1]: y2']
>>> table.rows[-2][1:3]
('1.0000', '')