This is documentation for Mathematica 8, which was
based on an earlier version of the Wolfram Language.
View current documentation (Version 11.2)

LeveneTest

LeveneTest[data]
tests whether the variance of data is 1.
LeveneTest
tests whether the variances of and are equal.
LeveneTest
tests a dispersion measure against .
LeveneTest
returns the value of .
  • LeveneTest performs a hypothesis test on data with null hypothesis that the true population variance , and alternative hypothesis that .
  • By default a probability value or -value is returned.
  • A small -value suggests that it is unlikely that is true.
  • The data must be univariate .
  • The argument can be any positive real number.
  • 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 returns a HypothesisTestData object htd that can be used to extract additional test results and properties using the form htd["property"].
  • LeveneTest can be used to directly give the value of .
  • 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
  • With {a1, ..., an}=Abs[data1-Mean[data1]] and {b1, ..., bm}=Abs[data2-Mean[data2]] the test statistic is given by where a=Mean[{a1, ...}], b=Mean[{b1, ...}], and c=Mean[{a1, ..., an, b1, ..., bm}]. The test statistic is assumed to follow FRatioDistribution under .
  • The following options can be used:
AlternativeHypothesis"Unequal"the inequality for the alternative hypothesis
SignificanceLevel0.05cutoff for diagnostics and reporting
VerifyTestAssumptionsAutomaticset which diagnostic tests to run
  • For the LeveneTest, a cutoff is chosen such that is rejected only if . The value of used for the and 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 .
"Normality"verify that all data is normally distributed
Test variances from two populations for equality:
Create a HypothesisTestData object for further property extraction:
Properties of the test:
Compare the variance of a population to a particular value:
Test against the alternative hypothesis :
Test variances from two populations for equality:
In[1]:=
Click for copyable input
In[2]:=
Click for copyable input
Out[2]=
Create a HypothesisTestData object for further property extraction:
In[3]:=
Click for copyable input
Out[3]=
Properties of the test:
In[4]:=
Click for copyable input
Out[4]=
 
Compare the variance of a population to a particular value:
In[1]:=
Click for copyable input
In[2]:=
Click for copyable input
Out[2]=
In[3]:=
Click for copyable input
Out[3]=
Test against the alternative hypothesis :
In[4]:=
Click for copyable input
Out[4]=
Test whether the variance of a population is 1:
The -values are typically large under :
The -values are typically small when is false:
Compare the variance of a population to a particular value:
Compare the variances of two populations:
The -values are typically large when the variances are equal:
The -values are typically small when the variances are not equal:
Test whether the ratio of the variances of two populations is a particular value:
The following forms are equivalent:
The order of the datasets should be considered when determining :
Create a HypothesisTestData object for repeated property extraction:
The properties available for extraction:
Extract some properties from a HypothesisTestData object:
The -value, test statistic, and degrees of freedom:
Extract any number of properties simultaneously:
The -value, test statistic, and degrees of freedom:
Tabulate test results:
The values from the table can be extracted using :
Tabulate -values or test statistics:
The -value from the table:
The test statistic from the table:
A two-sided test is performed by default:
Test versus :
Perform a two-sided test or a one-sided alternative:
Test versus :
Test versus :
Test versus :
Perform tests with one-sided alternatives when a null value is given:
Test versus :
Test versus :
Set the significance level for diagnostic tests:
By default is used:
The significance level is also used for and :
Diagnostics can be controlled as a group using All or None:
Verify all assumptions:
Check no assumptions:
Diagnostics can be controlled independently:
Check for normality:
It is often useful to bypass diagnostic tests for simulation purposes:
The assumptions of the test hold by design, so a great deal of time can be saved:
The results are identical:
Set up a test for constant error variance using Levene's test, which partitions the data into two equal pieces:
Generate some data for multiple regression analysis:
The residuals plotted against each predictor variable:
The first variable is positively correlated with its variance:
The Levene test is equivalent to FisherRatioTest when a single dataset is given:
Given a single dataset with length , the test statistic follows a ChiSquareDistribution under :
The maximum-likelihood estimate of the degrees of freedom is near :
Given two datasets with lengths and , the test statistic follows an FRatioDistribution under :
The Levene test is less sensitive to the assumption of normality than the FisherRatioTest:
The Fisher ratio test tends to underestimate the -value and commit more Type I errors:
The two-sample test statistic:
The Levene test assumes the data is drawn from a NormalDistribution:
Use ConoverTest or SiegelTukeyTest for non-normal data:
New in 8