ForecastComparisonResult._summary_table#

ForecastComparisonResult._summary_table()[source]#

Build the structured summary: the three tests as rows.

Under a header with the origin count, horizon, and mean differential; the notes read the sign, say which row to trust in short windows, state what the conditional row asks, and restate the nested-model caveat.

Return type:

SummaryTable

Returns:

The SummaryTable that summary(), str(), and the notebook renderer display.

Example

>>> import numpy as np
>>> rng = np.random.default_rng(0)
>>> a, b = rng.standard_normal(100) ** 2, rng.standard_normal(100) ** 2
>>> table = ForecastComparison(a, b).compute()._summary_table()
>>> [row[0] for row in table.rows]
['Diebold-Mariano', 'Harvey-Leybourne-Newbold', 'Giacomini-White (conditional)']