Presentation

This project contains functions and classes for statistical calculations, kernel computations and usual distribution computations (as probability distribution computation, random number generation...)

It is divided in three sub-projects :

The StatDesc sub-project contains functions and classes for computing the usual descriptive statistics,
The Kernel sub-project contains functions and classes for computing the usual kernels,
The Law sub-project contains functions and classes for usual probability density functions (or discrete probability distribution) computations, cumulative probability distribution, inverse cumulative distribution computations (quantile), random number generation.

Distributions laws

Density, log-density, cumulative distribution function, quantile function and random variate generation for many standard probability distributions are available in the Law sub-project. The complete list is

Bernoulli distribution,
Binomial distribution,
Categorical distribution,
Cauchy distribution,
Chi-squared distribution,
Exponential distribution,
Fisher-Snedecor distribution,
Gamma distribution,
Geometric distribution,
Hyper-Geometric distribution,
Normal distribution,
t-Student distribution,
Uniform distribution,
Weibull distribution.

All these distributions are implemented in the namespace STK::Law and derive from the Interface base class IUnivLaw and should implement the following pure virtual methods :

virtual Type rand() const =0;
virtual Real pdf(Type const& x) const =0;
virtual Real lpdf(Type const& x) const = 0;
virtual Real cdf(Real const& t) const =0;
virtual Real cdfc(Real const& t) const =0;
virtual Type icdf(Real const& p) const=0;

Multivariate Distributions laws

Support for some multivariate distribution laws is given.