UnivariateKuiperTest Method

Tests whether the sample is compatible with the given distribution.

Definition

Namespace: Meta.Numerics.Statistics
Assembly: Meta.Numerics (in Meta.Numerics.dll) Version: 4.2.0+6d77d64445f7d5d91b12e331399c4362ecb25333

C#

public static TestResult KuiperTest(
	this IReadOnlyList<double> sample,
	ContinuousDistribution distribution
)

VB

<ExtensionAttribute>
Public Shared Function KuiperTest ( 
	sample As IReadOnlyList(Of Double),
	distribution As ContinuousDistribution
) As TestResult

C++

public:
[ExtensionAttribute]
static TestResult^ KuiperTest(
	IReadOnlyList<double>^ sample, 
	ContinuousDistribution^ distribution
)

F#

[<ExtensionAttribute>]
static member KuiperTest : 
        sample : IReadOnlyList<float> * 
        distribution : ContinuousDistribution -> TestResult

Parameters

sample IReadOnlyListDouble: The sample.
distribution ContinuousDistribution: The distribution.

Return Value

TestResult
The test result. The test statistic is the V statistic and the chance to obtain such a large value of V under the assumption that the sample is drawn from the given distribution.

Usage Note

In Visual Basic and C#, you can call this method as an instance method on any object of type IReadOnlyListDouble. When you use instance method syntax to call this method, omit the first parameter. For more information, see Extension Methods (Visual Basic) or Extension Methods (C# Programming Guide).

Remarks

Like the Kolmogorov-Smirnov test (KolmogorovSmirnovTest(IReadOnlyListDouble, ContinuousDistribution)), Kuiper's test compares the EDF of the sample to the CDF of the given distribution. Unlike the Kolmogorov-Smirnov test, the Kuiper test satistic in invariant under re-definitions of the origin. It is thus particularly appropriate for circular distributions, although it can also be applied to non-periodic distributions.

For small sample sizes, we compute the null distribution of V exactly. For large sample sizes, we use an accurate asymptotic approximation. Therefore it is safe to use this method for all sample sizes.

Exceptions

ArgumentNullException	distribution is .
InsufficientDataException	There is no data in the sample.