pl.edu.agh.age.compute.ea.rand

Class GaussianGenerator.NormalCdf

java.lang.Object

pl.edu.agh.age.compute.ea.rand.GaussianGenerator.NormalCdf

Enclosing class:

GaussianGenerator

private static final class GaussianGenerator.NormalCdf
extends java.lang.Object

Helper class, encapsulate the inverse of the cdf of a normal distribution.

Field Summary

Fields

Modifier and Type	Field and Description
private static double[]	INV_NORMAL_2_P_1
private static double[]	INV_NORMAL_2_P_2
private static double[]	INV_NORMAL_2_P_3
private static double[]	INV_NORMAL_2_Q_1
private static double[]	INV_NORMAL_2_Q_2
private static double[]	INV_NORMAL_2_Q_3
private static double	RAC2
private static double	XBIG

Constructor Summary

Constructors

Modifier	Constructor and Description
private	NormalCdf()

Method Summary

Modifier and Type	Method and Description
private static double	getValue(double u) Returns the inverse of the cdf of the normal distribution.

Methods inherited from class java.lang.Object

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

Field Detail

RAC2

private static final double RAC2

See Also:

Constant Field Values

XBIG

private static final double XBIG

See Also:

Constant Field Values

INV_NORMAL_2_P_1

private static final double[] INV_NORMAL_2_P_1

INV_NORMAL_2_Q_1

private static final double[] INV_NORMAL_2_Q_1

INV_NORMAL_2_P_2

private static final double[] INV_NORMAL_2_P_2

INV_NORMAL_2_Q_2

private static final double[] INV_NORMAL_2_Q_2

INV_NORMAL_2_P_3

private static final double[] INV_NORMAL_2_P_3

INV_NORMAL_2_Q_3

private static final double[] INV_NORMAL_2_Q_3

Constructor Detail

NormalCdf

private NormalCdf()

Method Detail

getValue

private static double getValue(double u)

Returns the inverse of the cdf of the normal distribution. Rational approximations giving 16 decimals of precision. The authors also give an approximation with 23 decimals of precision. J.M. Blair, C.A. Edwards, J.H. Johnson, “Rational Chebyshev approximations for the Inverse of the Error Function”, in Mathematics of Computation, Vol. 30, 136, pp 827, (1976)

Parameters:

u - The argument