SpilloverResult._summary_table#

SpilloverResult._summary_table()[source]#

Build the structured summary.

Return type:

SummaryTable

Returns:

One row per variable with its to, from and signed net spillovers; the metadata carries the dimension, the horizon and the total index; the notes state the total in words, the decomposition’s provenance and its relative-share caveat, and the association-not-causation reading.

Example

>>> import numpy as np
>>> from cultivars.multivariate.reduced_form.vector_autoregression import VAR
>>> y = np.random.default_rng(0).standard_normal((150, 3))
>>> spill = Spillover(VAR(y, order=1).fit(), horizon=5).compute()
>>> table = spill._summary_table()
>>> table.title, len(table.rows), len(table.notes)
('Diebold-Yilmaz Connectedness', 3, 3)
>>> table.columns
('variable', 'to others', 'from others', 'net')
>>> table.metadata[1]
('Horizon', '5')