TVPSVARResult._summary_table#

TVPSVARResult._summary_table()[source]#

Build the structured summary.

Return type:

SummaryTable

Returns:

One row per equation with the absolute diagonal impact at the first and last dates; the metadata names the scheme, the reduced form and the draw count; the notes state where the ordering was declared (at estimation under SV, here otherwise), the frozen-at-t reading of irf, and the plug-in nature of the point summaries.

Example

>>> import numpy as np
>>> y = np.random.default_rng(0).standard_normal((120, 2))
>>> source = TVPVAR(y, order=1, training=30).fit(n_draws=20, n_burn=8, seed=0)
>>> table = TVPSVAR(source).identify()._summary_table()
>>> table.title, len(table.rows), len(table.notes)
('TVP-SVAR (TVP-VAR) Results', 2, 3)
>>> table.columns
('equation', '|impact| at start', '|impact| at end')
>>> table.metadata[:2]
(('Scheme', 'recursive'), ('Reduced form', 'TVP-VAR(1)'))
>>> table.rows[0][1] == table.rows[0][2]
True