Class CumulativeNormalInverse

All Implemented Interfaces:
Function<Vector,Double>, RealScalarFunction, UnivariateRealFunction

public class CumulativeNormalInverse extends AbstractUnivariateRealFunction
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:
  • Constructor Details

    • CumulativeNormalInverse

      public CumulativeNormalInverse()
  • Method Details

    • evaluate

      public double evaluate(double u)
      Description copied from interface: UnivariateRealFunction
      Evaluate y = f(x).
      u - x