cern.jet.random
Class Wald

java.lang.Object
  |
  +--cern.colt.PersistentObject
        |
        +--cern.jet.random.AbstractDistribution
              |
              +--cern.jet.random.AbstractContinousDistribution
                    |
                    +--cern.jet.random.Wald

All Implemented Interfaces:

java.lang.Cloneable, cern.colt.function.DoubleFunction, cern.colt.function.IntFunction, java.io.Serializable

public class Wald

extends AbstractContinousDistribution

Wald distribution; also called Inverse Gaussian distribution;

p(x) = sqrt(lambda/(2*pi*x^3)) * exp(-lambda*(x-mu)^2/(2*mu^2*x))

Valid parameter ranges: x,lambda > 0.

Instance methods operate on a user supplied uniform random number generator; they are unsynchronized.

Static methods operate on a default uniform random number generator; they are synchronized.

Implementation:

Method: Ratio of Uniforms with shift.

High performance implementation. This is a port of Random Number Generators by Professor Hossein Arsham. This implementation, in turn, is based on Michael, et al. (1976) as refered in Zabel's Dissertation

See Also:

Serialized Form

Field Summary

protected double	ch2
protected double	lam
protected double	mu
protected static Wald	shared

Fields inherited from class cern.jet.random.AbstractDistribution

randomGenerator

Constructor Summary

Wald(double m, double l, RandomElement randomGenerator)
Constructs a Wald distribution.

Method Summary

double	cdf(double x, double y) Returns the cumulative distribution function.
double	nextCh2(double freedom)
double	nextDouble() Returns a random number from the distribution.
double	nextDouble(double u, double lambda) Returns a random number from the distribution; bypasses the internal state.
double	pdf(double x) Returns the probability distribution function.
void	setState(double u, double lambda) Sets the distribution parameter.
static double	staticNextDouble(double u, double lambda) Returns a random number from the distribution.
java.lang.String	toString() Returns a String representation of the receiver.

Methods inherited from class cern.jet.random.AbstractDistribution

apply, apply, clone, getRandomGenerator, makeDefaultGenerator, nextInt, setRandomGenerator

Methods inherited from class java.lang.Object

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

Field Detail

mu

protected double mu

lam

protected double lam

ch2

protected double ch2

shared

protected static Wald shared

Constructor Detail

Wald

public Wald(double m,
            double l,
            RandomElement randomGenerator)

Constructs a Wald distribution. Example: m = 1.0, l = 1.0.

Parameters:

m - mean value.

l - scale parameter.

Throws:

java.lang.IllegalArgumentException - if mu, lambda < 0.0.

Method Detail

cdf

public double cdf(double x,
                  double y)

Returns the cumulative distribution function.

nextDouble

public double nextDouble()

Returns a random number from the distribution.

Specified by:

nextDouble in class AbstractDistribution

nextDouble

public double nextDouble(double u,
                         double lambda)

Returns a random number from the distribution; bypasses the internal state.

Parameters:

u - mean parameter

lambda - scale parameter It should hold mu, lambda > 0.

nextCh2

public double nextCh2(double freedom)

pdf

public double pdf(double x)

Returns the probability distribution function.

setState

public void setState(double u,
                     double lambda)

Sets the distribution parameter.

Parameters:

u - mean parameter^M

lambda - scale parameter^M

staticNextDouble

public static double staticNextDouble(double u,
                                      double lambda)

Returns a random number from the distribution.

Parameters:

u - mean parameter^M

lambda - scale parameter^M

toString

public java.lang.String toString()

Returns a String representation of the receiver.

Overrides:

toString in class java.lang.Object