GibbsBVARResult._summary_table#

GibbsBVARResult._summary_table()[source]#

Build the structured summary.

Return type:

SummaryTable

Returns:

One row per equation with the posterior mean and 68% interval of its own first lag; the metadata carries the prior, the draw bookkeeping, the dimensions and the dummy rows; the notes state the sampler, the marginal-likelihood scope, the stability share, the absence of criteria, the predictive semantics and – under an adaptive prior – the diagnostic that is available.

Example

>>> import numpy as np
>>> from cultivars.bayes.priors import SpikeAndSlabPrior
>>> y = np.random.default_rng(0).standard_normal((150, 2))
>>> table = GibbsBVAR(y, order=1).fit(n_draws=60, n_burn=20, seed=0)._summary_table()
>>> table.title, table.columns, len(table.rows), len(table.notes)
('Gibbs BVAR(1) Results', ('equation', 'own L1 mean', '68% interval'), 2, 5)
>>> table.metadata[2]
('Draws', '40 kept of 60')
>>> selected = GibbsBVAR(y, order=1, prior=SpikeAndSlabPrior()).fit(
...     n_draws=60, n_burn=20, seed=0
... )
>>> selected._summary_table().notes[0][:16]
'Selection prior:'