Kurtosis
✖
Kurtosis

Details


- Kurtosis measures the concentration of data around the peak and in the tails versus the concentration in the flanks.
- Kurtosis[…] is equivalent to CentralMoment[…,4]/CentralMoment[…,2]2.
- A normal distribution has kurtosis
equal to 3. In comparing shapes with normal we have:
-
more flat than normal, platykurtic like normal, mesokurtic more peaked than normal, leptokurtic - Kurtosis[{{x1,y1,…},{x2,y2,…},…}] gives {Kurtosis[{x1,x2,…}],Kurtosis[{y1,y2,…}],…}.
- Kurtosis handles both numerical and symbolic data.
- The data can have the following additional forms and interpretations:
-
Association the values (the keys are ignored) » SparseArray as an array, equivalent to Normal[data] » QuantityArray quantities as an array » WeightedData weighted mean, based on the underlying EmpiricalDistribution » EventData based on the underlying SurvivalDistribution » TimeSeries, TemporalData, … vector or array of values (the time stamps ignored) » Image,Image3D RGB channel's values or grayscale intensity value » Audio amplitude values of all channels » DateObject, TimeObject list of dates or list of times - For a random process proc, the kurtosis function can be computed for slice distribution at time t, SliceDistribution[proc,t], as β[t]=Kurtosis[SliceDistribution[proc,t]]. »


Examples
open allclose allBasic Examples (4)Summary of the most common use cases
Kurtosis for a list of values:

https://wolfram.com/xid/0mlj9yhaospg-d698z0


https://wolfram.com/xid/0mlj9yhaospg-n9n


https://wolfram.com/xid/0mlj9yhaospg-bpyuss

Kurtosis for a parametric distribution:

https://wolfram.com/xid/0mlj9yhaospg-cdzcrp

Scope (23)Survey of the scope of standard use cases
Basic Uses (7)
Exact input yields exact output:

https://wolfram.com/xid/0mlj9yhaospg-ug7y2


https://wolfram.com/xid/0mlj9yhaospg-bcry2t

Approximate input yields approximate output:

https://wolfram.com/xid/0mlj9yhaospg-xqxn3


https://wolfram.com/xid/0mlj9yhaospg-gnz3p9

Find the kurtosis of WeightedData:

https://wolfram.com/xid/0mlj9yhaospg-d0wc9z


https://wolfram.com/xid/0mlj9yhaospg-mab31

https://wolfram.com/xid/0mlj9yhaospg-gc8lnk

Find the kurtosis of EventData:

https://wolfram.com/xid/0mlj9yhaospg-kiuumt

https://wolfram.com/xid/0mlj9yhaospg-cv4d9n

Find the kurtosis of TemporalData:

https://wolfram.com/xid/0mlj9yhaospg-gx0rsr

https://wolfram.com/xid/0mlj9yhaospg-f5ij1t

https://wolfram.com/xid/0mlj9yhaospg-8e999

Find the kurtosis of TimeSeries:

https://wolfram.com/xid/0mlj9yhaospg-hf056t

The kurtosis depends only on the values:

https://wolfram.com/xid/0mlj9yhaospg-ikztk4

Find the kurtosis of data involving quantities:

https://wolfram.com/xid/0mlj9yhaospg-jopin9


https://wolfram.com/xid/0mlj9yhaospg-e8c21s

Array Data (5)
Kurtosis for a matrix gives columnwise kurtosis:

https://wolfram.com/xid/0mlj9yhaospg-ezu2uz


https://wolfram.com/xid/0mlj9yhaospg-nknun


https://wolfram.com/xid/0mlj9yhaospg-ma3v2m

When the input is an Association, Kurtosis works on its values:

https://wolfram.com/xid/0mlj9yhaospg-cs7n5q

https://wolfram.com/xid/0mlj9yhaospg-ddw92p


SparseArray data can be used just like dense arrays:

https://wolfram.com/xid/0mlj9yhaospg-n691tv


https://wolfram.com/xid/0mlj9yhaospg-drrysl

Find the kurtosis of a QuantityArray:

https://wolfram.com/xid/0mlj9yhaospg-lgwnaj


https://wolfram.com/xid/0mlj9yhaospg-k03qc6

Image and Audio Data (2)
Channelwise kurtosis value of an RGB image:

https://wolfram.com/xid/0mlj9yhaospg-ojba46

Mean intensity value of a grayscale image:

https://wolfram.com/xid/0mlj9yhaospg-ue2gq5

On audio objects, Kurtosis works channelwise:

https://wolfram.com/xid/0mlj9yhaospg-nq1jnz


https://wolfram.com/xid/0mlj9yhaospg-mjmudf


https://wolfram.com/xid/0mlj9yhaospg-bs38vd

Date and Time (5)

https://wolfram.com/xid/0mlj9yhaospg-b1smxx

https://wolfram.com/xid/0mlj9yhaospg-pa4nmn


https://wolfram.com/xid/0mlj9yhaospg-uok1il

Compute the weighted kurtosis of dates:

https://wolfram.com/xid/0mlj9yhaospg-c98kbd


https://wolfram.com/xid/0mlj9yhaospg-8c1had

https://wolfram.com/xid/0mlj9yhaospg-t71b2h

Compute the kurtosis of dates given in different calendars:

https://wolfram.com/xid/0mlj9yhaospg-wbzcuv


https://wolfram.com/xid/0mlj9yhaospg-9ius88

Compute the kurtosis of times:

https://wolfram.com/xid/0mlj9yhaospg-et9bla


https://wolfram.com/xid/0mlj9yhaospg-ztsexm

Compute the kurtosis of times with different time zone specifications:

https://wolfram.com/xid/0mlj9yhaospg-mrqghz


https://wolfram.com/xid/0mlj9yhaospg-1d7sk5

Distributions and Processes (4)
Find the kurtosis for univariate distributions:

https://wolfram.com/xid/0mlj9yhaospg-rxz55


https://wolfram.com/xid/0mlj9yhaospg-hbq28j


https://wolfram.com/xid/0mlj9yhaospg-lzwoz3

Kurtosis for derived distributions:

https://wolfram.com/xid/0mlj9yhaospg-rgc72x


https://wolfram.com/xid/0mlj9yhaospg-byqvvz


https://wolfram.com/xid/0mlj9yhaospg-215ry

https://wolfram.com/xid/0mlj9yhaospg-fq5ptk

Kurtosis for distributions with quantities:

https://wolfram.com/xid/0mlj9yhaospg-dqsioj


https://wolfram.com/xid/0mlj9yhaospg-b53jwg

Kurtosis function for a random process:

https://wolfram.com/xid/0mlj9yhaospg-c4ojmv


https://wolfram.com/xid/0mlj9yhaospg-g9pmgp

Applications (6)Sample problems that can be solved with this function
Normal distributions have Kurtosis value 3:

https://wolfram.com/xid/0mlj9yhaospg-lk6n95


https://wolfram.com/xid/0mlj9yhaospg-baih73

Leptokurtic distributions have kurtosis greater than 3:

https://wolfram.com/xid/0mlj9yhaospg-fbptm3


https://wolfram.com/xid/0mlj9yhaospg-c2fgfe


https://wolfram.com/xid/0mlj9yhaospg-vv0n

Platykurtic distributions have kurtosis less than 3:

https://wolfram.com/xid/0mlj9yhaospg-7pmt4p


https://wolfram.com/xid/0mlj9yhaospg-r1uz9k

The limiting distribution for BinomialDistribution as is normal:

https://wolfram.com/xid/0mlj9yhaospg-cjcacn


https://wolfram.com/xid/0mlj9yhaospg-ikcny4

The limiting value of the kurtosis is 3:

https://wolfram.com/xid/0mlj9yhaospg-9jqn7h

By the central limit theorem, kurtosis of normalized sums of random variables will converge to 3:

https://wolfram.com/xid/0mlj9yhaospg-o42rw3

https://wolfram.com/xid/0mlj9yhaospg-9gpzii

Define a Pearson distribution with zero mean and unit variance, parameterized by skewness and kurtosis:

https://wolfram.com/xid/0mlj9yhaospg-hshyga
Obtain parameter inequalities for Pearson types 1, 4, and 6:

https://wolfram.com/xid/0mlj9yhaospg-46zj1

The region plot for Pearson types depending on the values of skewness and kurtosis:

https://wolfram.com/xid/0mlj9yhaospg-26mr9
Generate a random sample from a ParetoDistribution:

https://wolfram.com/xid/0mlj9yhaospg-hp3zyw
Determine the type of PearsonDistribution with moments matching the sample moments:

https://wolfram.com/xid/0mlj9yhaospg-4eqpc

This time series contains the number of steps taken daily by a person during a period of five months:

https://wolfram.com/xid/0mlj9yhaospg-l8i1hu

https://wolfram.com/xid/0mlj9yhaospg-egrdpv


https://wolfram.com/xid/0mlj9yhaospg-h3rzfh

Analyze the kurtosis as an indication of consistency of daily steps taken:

https://wolfram.com/xid/0mlj9yhaospg-vvz2te

The histogram of the frequency of daily counts shows that distribution is mesokurtic:

https://wolfram.com/xid/0mlj9yhaospg-rfj1tf

https://wolfram.com/xid/0mlj9yhaospg-kqbpv6

Find the skewness for the heights of the children in a class:

https://wolfram.com/xid/0mlj9yhaospg-cevfij

https://wolfram.com/xid/0mlj9yhaospg-fllmtw

Kurtosis larger than 3 would indicate a distribution highly concentrated around the mean:

https://wolfram.com/xid/0mlj9yhaospg-celepo

Properties & Relations (5)Properties of the function, and connections to other functions
Kurtosis for data can be computed from CentralMoment:

https://wolfram.com/xid/0mlj9yhaospg-gpep5v

https://wolfram.com/xid/0mlj9yhaospg-pqqxoo


https://wolfram.com/xid/0mlj9yhaospg-dlb7nb

Kurtosis for a distribution can be computed from CentralMoment:

https://wolfram.com/xid/0mlj9yhaospg-b2gkzn

https://wolfram.com/xid/0mlj9yhaospg-j1ep1x


https://wolfram.com/xid/0mlj9yhaospg-gepfe5


https://wolfram.com/xid/0mlj9yhaospg-cjvav

Kurtosis is bounded from below by 1, as :

https://wolfram.com/xid/0mlj9yhaospg-e80pqb


https://wolfram.com/xid/0mlj9yhaospg-iwzhs

Normal distributions have Kurtosis value 3:

https://wolfram.com/xid/0mlj9yhaospg-b6a64i

Approximately normal distributions have Kurtosis values near 3:

https://wolfram.com/xid/0mlj9yhaospg-iyosfj

https://wolfram.com/xid/0mlj9yhaospg-pnkse2

Plot the PDF for the distribution:

https://wolfram.com/xid/0mlj9yhaospg-dp1jbq

Plot the PDF for the normal approximation:

https://wolfram.com/xid/0mlj9yhaospg-fakd7k

Possible Issues (2)Common pitfalls and unexpected behavior
Kurtosis coefficient is sometimes confused with excess kurtosis coefficient:

https://wolfram.com/xid/0mlj9yhaospg-chfdez
The excess kurtosis vanishes for NormalDistribution:

https://wolfram.com/xid/0mlj9yhaospg-tf168

Excess kurtosis is defined as Cumulant[dist,4]/Cumulant[dist,2]^2:

https://wolfram.com/xid/0mlj9yhaospg-cn3aeh

Kurtosis may be undefined for data:

https://wolfram.com/xid/0mlj9yhaospg-6xekyb


https://wolfram.com/xid/0mlj9yhaospg-616ki1

Kurtosis may be undefined for a distribution:

https://wolfram.com/xid/0mlj9yhaospg-wbvtjw

Neat Examples (1)Surprising or curious use cases
The distribution of Kurtosis estimates for 20, 100, and 300 samples:

https://wolfram.com/xid/0mlj9yhaospg-bk9tje


https://wolfram.com/xid/0mlj9yhaospg-8raem

Wolfram Research (2007), Kurtosis, Wolfram Language function, https://reference.wolfram.com/language/ref/Kurtosis.html (updated 2024).
Text
Wolfram Research (2007), Kurtosis, Wolfram Language function, https://reference.wolfram.com/language/ref/Kurtosis.html (updated 2024).
Wolfram Research (2007), Kurtosis, Wolfram Language function, https://reference.wolfram.com/language/ref/Kurtosis.html (updated 2024).
CMS
Wolfram Language. 2007. "Kurtosis." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2024. https://reference.wolfram.com/language/ref/Kurtosis.html.
Wolfram Language. 2007. "Kurtosis." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2024. https://reference.wolfram.com/language/ref/Kurtosis.html.
APA
Wolfram Language. (2007). Kurtosis. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/Kurtosis.html
Wolfram Language. (2007). Kurtosis. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/Kurtosis.html
BibTeX
@misc{reference.wolfram_2025_kurtosis, author="Wolfram Research", title="{Kurtosis}", year="2024", howpublished="\url{https://reference.wolfram.com/language/ref/Kurtosis.html}", note=[Accessed: 30-April-2025
]}
BibLaTeX
@online{reference.wolfram_2025_kurtosis, organization={Wolfram Research}, title={Kurtosis}, year={2024}, url={https://reference.wolfram.com/language/ref/Kurtosis.html}, note=[Accessed: 30-April-2025
]}