com.numericalmethod.suanshu.analysis.function.special.gaussian

Class CumulativeNormalInverse

java.lang.Object

com.numericalmethod.suanshu.analysis.function.rn2r1.univariate.UnivariateRealFunction

com.numericalmethod.suanshu.analysis.function.special.gaussian.CumulativeNormalInverse

All Implemented Interfaces:

Function<Vector,java.lang.Double>, RealScalarFunction, java.io.Serializable

public class CumulativeNormalInverse
extends UnivariateRealFunction

The inverse of the cumulative standard Normal distribution function is defined as: \[ N^{-1}(u) /]

This implementation uses the Beasley-Springer-Moro algorithm. It has a maximum absolute error of 3e-9 out to seven standard deviations. The error is maximal when u is around 0.5.

The R equivalent function is qnorm.

See Also:

• "Moro, B, The full monte. Risk 8 (Feb): 57-58, 1995"
• Wikipedia: Cumulative distribution function

, Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface com.numericalmethod.suanshu.analysis.function.Function

Function.EvaluationException

Constructor Summary

Constructors

Constructor and Description
CumulativeNormalInverse()

Method Summary

Modifier and Type	Method and Description
double	evaluate(double u) Evaluate y = f(x).

Methods inherited from class com.numericalmethod.suanshu.analysis.function.rn2r1.univariate.UnivariateRealFunction

dimensionOfDomain, dimensionOfRange, evaluate

Methods inherited from class java.lang.Object

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

Constructor Detail

CumulativeNormalInverse

public CumulativeNormalInverse()

Method Detail

evaluate

public double evaluate(double u)

Description copied from class: UnivariateRealFunction

Evaluate y = f(x).

Specified by:

evaluate in class UnivariateRealFunction

Parameters:

u - x

Returns:

f(x)