ComputeKolmogorovStatistics

ComputeKolmogorovStatistics(sample, distribution)

Compute the unscaled Kolmogorov distance between a sample and a distribution.

The distance is the maximum absolute deviation between the empirical CDF of the given sample and the CDF of the given distribution.

Parameters:

sample2-d float array

A continuous 1D distribution sample.

distributionDistribution

A continuous 1D distribution.

Returns:

distancefloat

The Kolmogorov distance.

Examples

>>> import openturns as ot
>>> ot.RandomGenerator.SetSeed(0)
>>> distribution = ot.Normal()
>>> sample = distribution.getSample(20)
>>> ot.FittingTest.ComputeKolmogorovStatistics(sample, distribution)
0.14727...