WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

LeveneTest
✖
LeveneTest

✖
LeveneTest[data]

tests whether the variance of data is 1.

✖
LeveneTest[{data1,data2,…}]

tests whether the variances of data1, data2, … are equal.

✖
LeveneTest[dspec,]

tests a dispersion measure against .

✖
LeveneTest[dspec,,"property"]

returns the value of "property".

Details and Options

  • LeveneTest tests the null hypothesis against the alternative hypothesis :
  • data
    {data1,data2}
    {data1,data2,…}not all equal
  • where σi2 is the population variance for datai.
  • By default, a probability value or -value is returned.
  • A small -value suggests that it is unlikely that is true.
  • The data in dspec must be univariate {x1,x2,…}.
  • The argument can be any positive real number. The default value of is 1 if not specified, and ignored if the number of groups in dspec is more than 2.
  • The LeveneTest assumes the data is normally distributed and, for the two-sample case, is much less sensitive to this assumption than the FisherRatioTest.
  • LeveneTest[data,,"HypothesisTestData"] returns a HypothesisTestData object htd that can be used to extract additional test results and properties using the form htd["property"].
  • LeveneTest[data,,"property"] can be used to directly give the value of "property".
  • Properties related to the reporting of test results include:
  • "DegreesOfFreedom"the degrees of freedom used in a test
    "PValue"list of -values
    "PValueTable"formatted table of -values
    "ShortTestConclusion"a short description of the conclusion of a test
    "TestConclusion"a description of the conclusion of a test
    "TestData"list of pairs of test statistics and -values
    "TestDataTable"formatted table of -values and test statistics
    "TestStatistic"list of test statistics
    "TestStatisticTable"formatted table of test statistics
  • When one sample of size is given, the LeveneTest is equivalent to the FisherRatioTest.
  • For the -sample case {data1,data2,…,datak} with datai={xi,1,xi,2,…,xi,ni}, the test statistic is given by , where zi,j=Abs[xi,j-Mean[datai]], zi=Mean[{zi,1,zi,2,…,zi,ni}], and z=Mean[{z1,z2,…,zk}]. The test statistic is assumed to follow FRatioDistribution[k-1,sum_(i=1)^k(ni-1)] under .
  • The following options can be used:
  • AlternativeHypothesis "Unequal"the inequality for the alternative hypothesis
    SignificanceLevel 0.05cutoff for diagnostics and reporting
    VerifyTestAssumptions Automaticset which diagnostic tests to run
  • For the LeveneTest, a cutoff is chosen such that is rejected only if . The value of used for the "TestConclusion" and "ShortTestConclusion" properties is controlled by the SignificanceLevel option. This value is also used in diagnostic tests of assumptions, including tests for normality and symmetry. By default, is set to 0.05.
  • Named settings for VerifyTestAssumptions in LeveneTest include:
  • "Normality"verify that all data is normally distributed

Examples

open allclose all

Basic Examples  (2)Summary of the most common use cases

Test variances from two populations for equality:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-kd5itj
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-lpfld5
Out[2]=2

Create a HypothesisTestData object for further property extraction:

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-ybn5y
Out[3]=3

Properties of the test:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-yfec
Out[4]=4

Compare the variance of a population to a particular value:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-lbi4hl
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-eocrh
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-c8qh6
Out[3]=3

Test against the alternative hypothesis :

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-dov9ba
Out[4]=4

Scope  (10)Survey of the scope of standard use cases

Testing  (8)

Test whether the variance of a population is 1:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-rausuz
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-5wf5k

The -value is uniformly distributed in [0,1] under :

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-dea8hq
Out[3]=3

The histogram of a sample of -values of the Levene test:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-mhkaek
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-ps9g5i
Out[5]=5

The -value is typically small when is false:

In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-fqzjg9
In[7]:=7
✖
https://wolfram.com/xid/01zbsjrfjja-qmkias
In[8]:=8
✖
https://wolfram.com/xid/01zbsjrfjja-g42zuc
Out[8]=8

Compare the variance of a population to a particular value:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-0x7z21
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-bev4t3
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-m689y
Out[3]=3
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-bzzuwt
Out[4]=4

Compare the variances of two populations:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-6qd6cf
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-mk1rwj

The -value is uniformly distributed in [0,1] under :

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-dcnktx
Out[3]=3

The histogram of a sample of -values of the Levene test:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-47e9dv
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-lahxcm
Out[5]=5

The -value is typically small when the variances are not equal:

In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-jgjgqh
In[7]:=7
✖
https://wolfram.com/xid/01zbsjrfjja-3jwr9q
In[8]:=8
✖
https://wolfram.com/xid/01zbsjrfjja-b15esj
Out[8]=8

Test whether the ratio of the variances of two populations is a particular value:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-nh4zv9
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-d2atk
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-qem1d

The following forms are equivalent:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-f4bmuo
Out[4]=4
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-gompwh
Out[5]=5

The order of the datasets should be considered when determining :

In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-6e1y8
Out[6]=6

Test whether the variances of three populations are identical:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-ean2ma
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-g4kkl
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-fg4d3t
Out[3]=3

Create a HypothesisTestData object for repeated property extraction:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-vo9sor
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-0x5m5
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-cc8eh1

The properties available for extraction:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-frvg20
Out[4]=4

Extract some properties from a HypothesisTestData object:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-j8zm7r
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-c03go
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-bpn9dr

The -value, test statistic, and degrees of freedom:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-365dq
Out[4]=4
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-bn5rjv
Out[5]=5
In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-cm9bof
Out[6]=6

Extract any number of properties simultaneously:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-onp01a
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-bycagv
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-dmu6hk

The -value, test statistic, and degrees of freedom:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-i6fwj7
Out[4]=4

Reporting  (2)

Tabulate test results:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-j7ol0s
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-ba6zb1
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-hb1mu5
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-hh3kq
Out[4]=4

The values from the table can be extracted using "TestData":

In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-25755
Out[5]=5

Tabulate -values or test statistics:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-39b2t0
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-fr3ezf
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-blo8x
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-g8i1dt
Out[4]=4

The -value from the table:

In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-o0wuj
Out[5]=5
In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-kx4361
Out[6]=6

The test statistic from the table:

In[7]:=7
✖
https://wolfram.com/xid/01zbsjrfjja-bitsqd
Out[7]=7

Options  (8)Common values & functionality for each option

AlternativeHypothesis  (3)

A two-sided test is performed by default:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-bgoxnx

Test versus :

In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-he0w0s
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-jqt2u8
Out[3]=3

Perform a two-sided test or a one-sided alternative:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-kwmm8d

Test versus :

In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-dy0fuc
Out[2]=2

Test versus :

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-g8h639
Out[3]=3

Test versus :

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-f19ykz
Out[4]=4

Perform tests with one-sided alternatives when a null value is given:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-cay5xk
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-v01gr
Out[2]=2

Test versus :

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-ci67wa
Out[3]=3

Test versus :

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-m3sbc
Out[4]=4

SignificanceLevel  (2)

Set the significance level for diagnostic tests:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-fn2ahc
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-dwfi1
Out[2]=2

By default, 0.05 is used:

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-cod4ca
Out[3]=3

The significance level is also used for "TestConclusion" and "ShortTestConclusion":

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-bhkod7
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-lasldz
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-hykroc
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-bvt7nt
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-hpqqgh
In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-flavjg
Out[6]=6
In[7]:=7
✖
https://wolfram.com/xid/01zbsjrfjja-m2oyg2
Out[7]=7

VerifyTestAssumptions  (3)

Diagnostics can be controlled as a group using All or None:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-ma0mld

Verify all assumptions:

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-bg3dnp
Out[3]=3

Check no assumptions:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-foxivl
Out[4]=4

Diagnostics can be controlled independently:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-btjvx7

Check for normality:

In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-djybum
Out[2]=2

Set the normality assumption to True:

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-ioa6i3
Out[3]=3

It is often useful to bypass diagnostic tests for simulation purposes:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-kfpeh6
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-cxjgtt
Out[2]=2

The assumptions of the test hold by design, so a great deal of time can be saved:

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-cmfh98
Out[3]=3

The results are identical:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-btr43n
Out[4]=4

Applications  (1)Sample problems that can be solved with this function

Set up a test for constant error variance using Levene's test, which partitions the data into two equal pieces:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-fmr6yi

Generate some data for multiple regression analysis:

In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-dcu86
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-d01rfi

The residuals plotted against each predictor variable:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-bw7qbg
Out[4]=4
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-bclc9k

The first variable is positively correlated with its variance:

In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-eik5un
Out[6]=6

Properties & Relations  (8)Properties of the function, and connections to other functions

The Levene test is equivalent to FisherRatioTest when a single dataset is given:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-q3di42
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-j5fqwv
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-kub30
Out[3]=3
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-fvhuu5
Out[4]=4

Given a single dataset with length , the test statistic follows a ChiSquareDistribution[n-1] under :

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-dcdb2r
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-fnfl43
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-b8509h
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-lqhzmf
Out[4]=4

The maximum-likelihood estimate of the degrees of freedom is near :

In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-bq1j1i
Out[5]=5
In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-46lw9
Out[6]=6

Given two datasets with lengths and , the test statistic follows an FRatioDistribution[1,n+m-2] under :

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-mjh6vh
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-naqqrz
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-hkcfe1
Out[3]=3
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-bvu6jc
Out[4]=4

The Levene test is less sensitive to the assumption of normality than the FisherRatioTest:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-b5a6xr
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-hvtvke
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-40l62
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-d36rxi

The Fisher ratio test tends to underestimate the -value and commit more Type I errors:

In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-f0xgxt
Out[5]=5

The two-sample test statistic:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-haesu6
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-8bjjrh
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-bqhrkb
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-dgwwe
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-91x6y
In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-enkakr
Out[6]=6
In[7]:=7
✖
https://wolfram.com/xid/01zbsjrfjja-dl9jp
Out[7]=7

The three-sample test statistic:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-fq0ely
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-1ntapz
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-kwhhvy
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-idenw6
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-ejhx8d
In[6]:=6
✖
https://wolfram.com/xid/01zbsjrfjja-lvlhgt
Out[6]=6
In[7]:=7
✖
https://wolfram.com/xid/01zbsjrfjja-f0by32
Out[7]=7

The Levene test works with the values only when the input is a TimeSeries:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-7py5sj
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-57bf57
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-vvd88
Out[3]=3

The Levene test works with all the values together when the input is a TemporalData:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-qry3ls
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-b1l4g0
Out[2]=2

Test all the values only:

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-t6toez
Out[3]=3

Test whether the variances of the two paths are equal:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-kxzwhd
In[5]:=5
✖
https://wolfram.com/xid/01zbsjrfjja-jdvl55
Out[5]=5

Possible Issues  (3)Common pitfalls and unexpected behavior

The Levene test assumes the data is drawn from a NormalDistribution:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-b36obx
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-kddjr2
Out[2]=2

Use ConoverTest or SiegelTukeyTest for non-normal data:

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-ee5if9
Out[3]=3
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-1yubo
Out[4]=4

The Levene test ignores the argument when there are more than 2 groups:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-ci0pq0
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-zpcoai
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-pihxsk
Out[3]=3

When there are more than 2 groups in the data, the Levene test only allows the two-sided test for the alternative hypothesis:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-dxk2k3
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-comr9a
Out[2]=2
In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-l6buo
Out[3]=3
In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-csh51
Out[4]=4

Neat Examples  (1)Surprising or curious use cases

Compute the statistic when the null hypothesis is true:

In[1]:=1
✖
https://wolfram.com/xid/01zbsjrfjja-2qqg3c
In[2]:=2
✖
https://wolfram.com/xid/01zbsjrfjja-ywy3ty

The test statistic given a particular alternative:

In[3]:=3
✖
https://wolfram.com/xid/01zbsjrfjja-c5cy2n

Compare the distributions of the test statistics:

In[4]:=4
✖
https://wolfram.com/xid/01zbsjrfjja-87eb6q
Out[4]=4
Wolfram Research (2010), LeveneTest, Wolfram Language function, https://reference.wolfram.com/language/ref/LeveneTest.html (updated 2017).
✖
Wolfram Research (2010), LeveneTest, Wolfram Language function, https://reference.wolfram.com/language/ref/LeveneTest.html (updated 2017).

Text

Wolfram Research (2010), LeveneTest, Wolfram Language function, https://reference.wolfram.com/language/ref/LeveneTest.html (updated 2017).

✖
Wolfram Research (2010), LeveneTest, Wolfram Language function, https://reference.wolfram.com/language/ref/LeveneTest.html (updated 2017).

CMS

Wolfram Language. 2010. "LeveneTest." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2017. https://reference.wolfram.com/language/ref/LeveneTest.html.

✖
Wolfram Language. 2010. "LeveneTest." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2017. https://reference.wolfram.com/language/ref/LeveneTest.html.

APA

Wolfram Language. (2010). LeveneTest. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/LeveneTest.html

✖
Wolfram Language. (2010). LeveneTest. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/LeveneTest.html

BibTeX

@misc{reference.wolfram_2025_levenetest, author="Wolfram Research", title="{LeveneTest}", year="2017", howpublished="\url{https://reference.wolfram.com/language/ref/LeveneTest.html}", note=[Accessed: 26-March-2025 ]}

✖
@misc{reference.wolfram_2025_levenetest, author="Wolfram Research", title="{LeveneTest}", year="2017", howpublished="\url{https://reference.wolfram.com/language/ref/LeveneTest.html}", note=[Accessed: 26-March-2025 ]}

BibLaTeX

@online{reference.wolfram_2025_levenetest, organization={Wolfram Research}, title={LeveneTest}, year={2017}, url={https://reference.wolfram.com/language/ref/LeveneTest.html}, note=[Accessed: 26-March-2025 ]}

✖
@online{reference.wolfram_2025_levenetest, organization={Wolfram Research}, title={LeveneTest}, year={2017}, url={https://reference.wolfram.com/language/ref/LeveneTest.html}, note=[Accessed: 26-March-2025 ]}