org.apache.commons.math3.random

Class StableRandomGenerator

java.lang.Object

org.apache.commons.math3.random.StableRandomGenerator

All Implemented Interfaces:

NormalizedRandomGenerator

public class StableRandomGenerator
extends java.lang.Object
implements NormalizedRandomGenerator

This class provides a stable normalized random generator. It samples from a stable distribution with location parameter 0 and scale 1.

The implementation uses the Chambers-Mallows-Stuck method as described in Handbook of computational statistics: concepts and methods by James E. Gentle, Wolfgang Härdle, Yuichi Mori.

Since:

3.0

Field Summary

Fields

Modifier and Type	Field and Description
private double	alpha stability parameter
private double	beta skewness parameter
private RandomGenerator	generator Underlying generator.
private double	zeta cache of expression value used in generation

Constructor Summary

Constructors

Constructor and Description
StableRandomGenerator(RandomGenerator generator, double alpha, double beta) Create a new generator.

Method Summary

Methods

Modifier and Type	Method and Description
double	nextNormalizedDouble() Generate a random scalar with zero location and unit scale.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

generator

private final RandomGenerator generator

Underlying generator.

alpha

private final double alpha

stability parameter

beta

private final double beta

skewness parameter

zeta

private final double zeta

cache of expression value used in generation

Constructor Detail

StableRandomGenerator

public StableRandomGenerator(RandomGenerator generator,
                     double alpha,
                     double beta)
                      throws NullArgumentException,
                             OutOfRangeException

Create a new generator.

Parameters:

generator - underlying random generator to use

alpha - Stability parameter. Must be in range (0, 2]

beta - Skewness parameter. Must be in range [-1, 1]

Throws:

NullArgumentException - if generator is null

OutOfRangeException - if alpha <= 0 or alpha > 2 or beta < -1 or beta > 1

Method Detail

nextNormalizedDouble

public double nextNormalizedDouble()

Generate a random scalar with zero location and unit scale.

Specified by:

nextNormalizedDouble in interface NormalizedRandomGenerator

Returns:

a random scalar with zero location and unit scale