RandomSamplingExtensions.CorrelatedSamples Method

Definition

Namespace: Numerics.NET.Statistics.Distributions
Assembly: Numerics.NET (in Numerics.NET.dll) Version: 10.9.0

Overload List

CorrelatedSamples(IRandomSource, Int32, Distribution[], SymmetricMatrix<Double>)	Generates a series of random variables with the specified correlation matrix.
CorrelatedSamples(Random, Int32, Distribution[], SymmetricMatrix<Double>)	Generates a series of random variables with the specified correlation matrix.
CorrelatedSamples<TGenerator>(IRandomSource<TGenerator>, Int32, Distribution[], SymmetricMatrix<Double>)	Generates a series of random variables with the specified correlation matrix.

CorrelatedSamples(IRandomSource, Int32, Distribution[], SymmetricMatrix<Double>)

Generates a series of random variables with the specified correlation matrix.

public static Vector<double>[] CorrelatedSamples(
	this IRandomSource random,
	int numberOfSamples,
	Distribution[] distributions,
	SymmetricMatrix<double> correlations
)

Visual Basic

<ExtensionAttribute>
Public Shared Function CorrelatedSamples ( 
	random As IRandomSource,
	numberOfSamples As Integer,
	distributions As Distribution(),
	correlations As SymmetricMatrix(Of Double)
) As Vector(Of Double)()

C++/CLI

public:
[ExtensionAttribute]
static array<Vector<double>^>^ CorrelatedSamples(
	IRandomSource^ random, 
	int numberOfSamples, 
	array<Distribution^>^ distributions, 
	SymmetricMatrix<double>^ correlations
)

[<ExtensionAttribute>]
static member CorrelatedSamples : 
        random : IRandomSource * 
        numberOfSamples : int * 
        distributions : Distribution[] * 
        correlations : SymmetricMatrix<float> -> Vector<float>[]

Parameters

random IRandomSource
numberOfSamples Int32: The number of samples to generate. Must be at least two and greater than the number of distributions.
distributions Distribution[]: An array of Distribution objects specifying the probability distribution of each variable.
correlations SymmetricMatrix<Double>: A SymmetricMatrix specifying the desired correlation matrix.

Return Value

Vector<Double>[]
An array of real vectors with approximately the specified correlation matrix.

Usage Note

In Visual Basic and C#, you can call this method as an instance method on any object of type IRandomSource. 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

Uses Iman-Conover rank rearrangement, preserving every sampled marginal value. The correlation matrix must be finite and positive definite with a unit diagonal. The sample count must exceed the number of distributions. Singular normal-score permutations are retried a bounded number of times.

Exceptions

ArgumentNullException	The receiver, distributions, or correlations are null.
ArgumentOutOfRangeException	The sample count is less than two.
InsufficientDataException	The sample count does not exceed the number of distributions.
DimensionMismatchException	The matrix dimension differs from the distribution count.
ArgumentException	The marginal list is empty, contains null, or the matrix is invalid.
NotSupportedException	A marginal is not a univariate continuous or discrete distribution.
InvalidOperationException	Independent normal-score permutations could not be generated.

CorrelatedSamples<TGenerator>(IRandomSource<TGenerator>, Int32, Distribution[], SymmetricMatrix<Double>)

Generates a series of random variables with the specified correlation matrix.

public static Vector<double>[] CorrelatedSamples<TGenerator>(
	this IRandomSource<TGenerator> random,
	int numberOfSamples,
	Distribution[] distributions,
	SymmetricMatrix<double> correlations
)
where TGenerator : struct, new(), IRandomGenerator

Visual Basic

<ExtensionAttribute>
Public Shared Function CorrelatedSamples(Of TGenerator As {Structure, New, IRandomGenerator}) ( 
	random As IRandomSource(Of TGenerator),
	numberOfSamples As Integer,
	distributions As Distribution(),
	correlations As SymmetricMatrix(Of Double)
) As Vector(Of Double)()

C++/CLI

public:
[ExtensionAttribute]
generic<typename TGenerator>
where TGenerator : value class, gcnew(), IRandomGenerator
static array<Vector<double>^>^ CorrelatedSamples(
	IRandomSource<TGenerator>^ random, 
	int numberOfSamples, 
	array<Distribution^>^ distributions, 
	SymmetricMatrix<double>^ correlations
)

[<ExtensionAttribute>]
static member CorrelatedSamples : 
        random : IRandomSource<'TGenerator> * 
        numberOfSamples : int * 
        distributions : Distribution[] * 
        correlations : SymmetricMatrix<float> -> Vector<float>[]  when 'TGenerator : struct, new() and IRandomGenerator

Parameters

random IRandomSource<TGenerator>
numberOfSamples Int32: The number of samples to generate. Must be at least two and greater than the number of distributions.
distributions Distribution[]: An array of Distribution objects specifying the probability distribution of each variable.
correlations SymmetricMatrix<Double>: A SymmetricMatrix specifying the desired correlation matrix.

Type Parameters

TGenerator

Return Value

Vector<Double>[]
An array of real vectors with approximately the specified correlation matrix.

Usage Note

In Visual Basic and C#, you can call this method as an instance method on any object of type IRandomSource<TGenerator>. 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

Exceptions

ArgumentNullException	The receiver, distributions, or correlations are null.
ArgumentOutOfRangeException	The sample count is less than two.
InsufficientDataException	The sample count does not exceed the number of distributions.
DimensionMismatchException	The matrix dimension differs from the distribution count.
ArgumentException	The marginal list is empty, contains null, or the matrix is invalid.
NotSupportedException	A marginal is not a univariate continuous or discrete distribution.
InvalidOperationException	Independent normal-score permutations could not be generated.

CorrelatedSamples(Random, Int32, Distribution[], SymmetricMatrix<Double>)

Generates a series of random variables with the specified correlation matrix.

public static Vector<double>[] CorrelatedSamples(
	this Random random,
	int numberOfSamples,
	Distribution[] distributions,
	SymmetricMatrix<double> correlations
)

Visual Basic

<ExtensionAttribute>
Public Shared Function CorrelatedSamples ( 
	random As Random,
	numberOfSamples As Integer,
	distributions As Distribution(),
	correlations As SymmetricMatrix(Of Double)
) As Vector(Of Double)()

C++/CLI

public:
[ExtensionAttribute]
static array<Vector<double>^>^ CorrelatedSamples(
	Random^ random, 
	int numberOfSamples, 
	array<Distribution^>^ distributions, 
	SymmetricMatrix<double>^ correlations
)

[<ExtensionAttribute>]
static member CorrelatedSamples : 
        random : Random * 
        numberOfSamples : int * 
        distributions : Distribution[] * 
        correlations : SymmetricMatrix<float> -> Vector<float>[]

Parameters

random Random
numberOfSamples Int32: The number of samples to generate. Must be at least two and greater than the number of distributions.
distributions Distribution[]: An array of Distribution objects specifying the probability distribution of each variable.
correlations SymmetricMatrix<Double>: A SymmetricMatrix specifying the desired correlation matrix.

Return Value

Vector<Double>[]
An array of real vectors with approximately the specified correlation matrix.

Usage Note

In Visual Basic and C#, you can call this method as an instance method on any object of type Random. 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

Exceptions

ArgumentNullException	The receiver, distributions, or correlations are null.
ArgumentOutOfRangeException	The sample count is less than two.
InsufficientDataException	The sample count does not exceed the number of distributions.
DimensionMismatchException	The matrix dimension differs from the distribution count.
ArgumentException	The marginal list is empty, contains null, or the matrix is invalid.
NotSupportedException	A marginal is not a univariate continuous or discrete distribution.
InvalidOperationException	Independent normal-score permutations could not be generated.

RandomSamplingExtensions.CorrelatedSamples Method

Definition

Overload List

CorrelatedSamples(IRandomSource, Int32, Distribution[], SymmetricMatrix<Double>)

Parameters

Return Value

Usage Note

Remarks

Exceptions

CorrelatedSamples<TGenerator>(IRandomSource<TGenerator>, Int32, Distribution[], SymmetricMatrix<Double>)

Parameters

Type Parameters

Return Value

Usage Note

Remarks

Exceptions

CorrelatedSamples(Random, Int32, Distribution[], SymmetricMatrix<Double>)

Parameters

Return Value

Usage Note

Remarks

Exceptions

See Also

Reference