Package org.apache.commons.rng.sampling.distribution

Class ChengBetaSampler.BaseChengBetaSampler

java.lang.Object

org.apache.commons.rng.sampling.distribution.ChengBetaSampler.BaseChengBetaSampler

All Implemented Interfaces:

ContinuousSampler, SharedStateContinuousSampler, SharedStateSampler<SharedStateContinuousSampler>

Direct Known Subclasses:

ChengBetaSampler.ChengBBBetaSampler, ChengBetaSampler.ChengBCBetaSampler

Enclosing class:

ChengBetaSampler

private abstract static class ChengBetaSampler.BaseChengBetaSampler
extends java.lang.Object
implements SharedStateContinuousSampler

Base class to implement Cheng's algorithms for the beta distribution.

Field Summary

Fields

Modifier and Type	Field	Description
protected double	a	First shape parameter.
protected boolean	aIsAlphaShape	Flag set to true if a is the beta distribution alpha shape parameter.
protected double	alpha	The algorithm alpha factor.
protected double	b	Second shape parameter.
protected double	logAlpha	The logarithm of the alpha factor.
protected UniformRandomProvider	rng	Underlying source of randomness.

Constructor Summary

Constructors

Constructor	Description
BaseChengBetaSampler(UniformRandomProvider rng, boolean aIsAlphaShape, double a, double b)
BaseChengBetaSampler(UniformRandomProvider rng, ChengBetaSampler.BaseChengBetaSampler source)

Method Summary

Modifier and Type	Method	Description
protected double	computeX(double w)	Compute the sample result X.
java.lang.String	toString()

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.apache.commons.rng.sampling.distribution.ContinuousSampler

sample, samples, samples

Methods inherited from interface org.apache.commons.rng.sampling.SharedStateSampler

withUniformRandomProvider

Field Detail

aIsAlphaShape

protected final boolean aIsAlphaShape

Flag set to true if a is the beta distribution alpha shape parameter. Otherwise a is the beta distribution beta shape parameter.

From the original Cheng paper this is equal to the result of: a == a0.

a

protected final double a

First shape parameter. The meaning of this is dependent on the aIsAlphaShape flag.

b

protected final double b

Second shape parameter. The meaning of this is dependent on the aIsAlphaShape flag.

rng

protected final UniformRandomProvider rng

Underlying source of randomness.

alpha

protected final double alpha

The algorithm alpha factor. This is not the beta distribution alpha shape parameter. It is the sum of the two shape parameters (a + b.

logAlpha

protected final double logAlpha

The logarithm of the alpha factor.

Constructor Detail

BaseChengBetaSampler

BaseChengBetaSampler(UniformRandomProvider rng,
                     boolean aIsAlphaShape,
                     double a,
                     double b)

Parameters:

rng - Generator of uniformly distributed random numbers.

aIsAlphaShape - true if a is the beta distribution alpha shape parameter.

a - Distribution first shape parameter.

b - Distribution second shape parameter.

BaseChengBetaSampler

BaseChengBetaSampler(UniformRandomProvider rng,
                     ChengBetaSampler.BaseChengBetaSampler source)

Parameters:

rng - Generator of uniformly distributed random numbers.

source - Source to copy.

Method Detail

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

computeX

protected double computeX(double w)

Compute the sample result X.

If a == a0 deliver X = W/(b + W); otherwise deliver X = b/(b + W).

The finalisation step is shared between the BB and BC algorithm (as step 5 of the BB algorithm and step 6 of the BC algorithm).

Parameters:

w - Algorithm value W.

Returns:

the sample value