Public Member Functions |
Static Public Member Functions |
Protected Member Functions |
Protected Attributes |
List of all members
npstat::CompositeDistribution1D Class Reference
Inheritance diagram for npstat::CompositeDistribution1D:
Detailed DescriptionThis class represents univariate statistical distributions whose cumulative distribution functions F(x) can be built by composition of two other cumulative distribution functions: F(x) = G(H(x)). Naturally, G must correspond to a density supported on the interval [0, 1]. This density is often easier to fit (or to represent nonparametrically) than the original one in case H(x) is well chosen. The corresponding technique is known in the KDE-related literature as the "nonparametric transformations" method. See, for example, "A Comparison of Higher-Order Bias Kernel Density Estimators" by M.C. Jones and D.F. Signorini, JASA, Vol. 92, No. 439, p. 1063 (1997). Constructor & Destructor Documentation◆ CompositeDistribution1D()
Constructor arguments are the distributions used to build this composite. The support of pG must be the [0, 1] interval. Member Function Documentation◆ cdf()
Cumulative distribution function Implements npstat::AbsDistribution1D. ◆ classId()
Method needed for "geners" I/O Implements npstat::AbsDistribution1D. ◆ clone()
"Virtual copy constructor" Implements npstat::AbsDistribution1D. Reimplemented in npstat::JohnsonLadder, npstat::BinnedCompositeJohnson, npstat::LogQuadraticLadder, npstat::BetaGauss1D, and npstat::CompositeGauss1D. ◆ density()
Probability density Implements npstat::AbsDistribution1D. ◆ exceedance()
Exceedance (i.e., 1 - cdf) Implements npstat::AbsDistribution1D. ◆ G()
Fetch the distribution with support on [0, 1] ◆ H()
Fetch the distribution with arbitrary support ◆ isEqual()
Comparison for equality. To be implemented by derived classes. Implements npstat::AbsDistribution1D. ◆ quantile()
Quantile function Implements npstat::AbsDistribution1D. The documentation for this class was generated from the following file: Generated by 1.9.1 |