  # scipy stats.kurtosistest () function | python

NumPy | Python Methods and Functions

What is kurtosis?
This is the fourth central point divided by the square of the variance. This is a measure of "closeness", that is, a descriptor of the form of the probability distribution of a real random variable. Simply put, it can be said to be a measure of how a heavy tail compares to a normal distribution.

Its formula is —

Parameters:
array: Input array or object having the elements.
axis: Axis along which the kurtosistest is to be computed. By default axis = 0.

Returns: Z-score (Statistics value) and P-value for the normally distributed data set.

Code # 1:

 ` # Graph using numpy.linspace () ` ` # finding kurtosa `   ` from ` ` scipy.stats ` ` import ` ` kurtosistest ` ` import ` ` numpy as np ` ` import ` ` pylab as p `   ` x1 ` ` = ` ` np.linspace (` ` - ` ` 5 ` , ` 5 ` `, ` ` 1000 ` `) ` ` y1 ` ` = ` ` 1. ` ` / ` ` (np.sqrt (` ` 2. ` ` * ` ` np.pi)) ` ` * ` ` np.exp (` ` - ` `. ` ` 5 ` ` * ` ` (x1) ` ` * ` ` * ` ` 2 ` `) `   ` p.plot (x1, y1, ` ` `*` ` `) ` ` `  ` `  ` print ` ` (` `` Kurtosis for normal distribution: `` `, kurtosistest (y1)) `

Output:

`     Kurtosis for normal distribution: KurtosistestResult (statistic = -2.2557936070461615, pvalue = 0.024083559905734513) `