non_credibility_index

probnumeval.timeseries.non_credibility_index(approximate_solution, reference_solution, locations)

Compute the non-credibility index (NCI).

The NCI indicates how credible an estimate is. The smaller this value, the better. The NCI of a perfectly credible estimator is zero. Unlike the inclination index, the NCI cannot determine over- and underconfidence.

Parameters

• approximate_solution (TimeSeriesPosterior) – Approximate solution as returned by a Kalman filter or ODE solver. This must be a FiltSmoothPosterior.

• reference_solution (Callable[[ndarray], ndarray]) – Reference solution. (This is not assumed to be a TimeSeriesPosterior, because ideally this is the true solution of a problem; often, it is a reference solution computed with a non-probabilistic algorithm.)

• locations (ndarray) – Set of locations on which to evaluate the statistic.

Returns

Return type

NCI statistic.

See also

anees()

An alternative calibration measure.