scipy.stats.kurtosistest

scipy.stats.kurtosistest(a, axis=0, nan_policy='propagate')

Test whether a dataset has normal kurtosis.

This function tests the null hypothesis that the kurtosis of the population from which the sample was drawn is that of the normal distribution: kurtosis = 3(n-1)/(n+1).

Parameters

aarray

Array of the sample data.

axisint or None, optional

Axis along which to compute test. Default is 0. If None, compute over the whole array a.

nan_policy{‘propagate’, ‘raise’, ‘omit’}, optional

Defines how to handle when input contains nan. The following options are available (default is ‘propagate’):

• ‘propagate’: returns nan

• ‘raise’: throws an error

• ‘omit’: performs the calculations ignoring nan values

Returns

statisticfloat

The computed z-score for this test.

pvaluefloat

The two-sided p-value for the hypothesis test.

Notes

Valid only for n>20. This function uses the method described in [1].

References

1

see e.g. F. J. Anscombe, W. J. Glynn, “Distribution of the kurtosis statistic b2 for normal samples”, Biometrika, vol. 70, pp. 227-234, 1983.

Examples

>>> from scipy.stats import kurtosistest
>>> kurtosistest(list(range(20)))
KurtosistestResult(statistic=-1.7058104152122062, pvalue=0.08804338332528348)

>>> np.random.seed(28041990)
>>> s = np.random.normal(0, 1, 1000)
>>> kurtosistest(s)
KurtosistestResult(statistic=1.2317590987707365, pvalue=0.21803908613450895)