org.jquantlib.math.distributions

Class BivariateNormalDistribution

java.lang.Object

org.jquantlib.math.distributions.BivariateNormalDistribution

All Implemented Interfaces:

Ops.BinaryDoubleOp

public class BivariateNormalDistribution
extends java.lang.Object
implements Ops.BinaryDoubleOp

Cumulative bivariate normal distibution function (West 2004).

The bivariate normal distribution is a distribution of a pair of variables whose conditional distributions are normal and that satisfy certain other technical conditions.

The implementation derives from the article "Better Approximations To Cumulative Normal Distibutions", Graeme West, Dec 2004 available at www.finmod.co.za. Also available in Wilmott Magazine, 2005, (May), 70-76, The main code is a port of the C++ code at www.finmod.co.za/cummnorm.zip.

The algorithm is based on the near double-precision algorithm described in "Numerical Computation of Rectangular Bivariate an Trivariate Normal and t Probabilities", Genz (2004), Statistics and Computing 14, 151-160. (available at www.math.wsu.edu/faculty/genz/papers/bvnt/bvnt.html)

The standard bivariate normal distribution function is given by

This implementation mainly differs from the original code in two regards;

1. The implementation of the cumulative normal distribution is CumulativeNormalDistribution
2. The arrays XX and W are zero-based

Constructor Summary

Constructors

Constructor and Description
BivariateNormalDistribution(double rho) Constructor of BivariateNormalDistribution to initialize the correlation.

Method Summary

Modifier and Type	Method and Description
double	op(double x, double y) Computes the Bivariate Normal Distribution of the two variables x and y which can be correlated in a particular manner.

Methods inherited from class java.lang.Object

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

Constructor Detail

BivariateNormalDistribution

public BivariateNormalDistribution(double rho)

Constructor of BivariateNormalDistribution to initialize the correlation. The correlation rho must be >=-1.0 and <=1.0.

Parameters:

rho - correlation

Method Detail

op

public double op(double x,
                 double y)

Computes the Bivariate Normal Distribution of the two variables x and y which can be correlated in a particular manner.

Specified by:

op in interface Ops.BinaryDoubleOp

Parameters:

x - First variable

y - Second variable

Returns:

BVN