npstat::SeriesCGF1D Class Reference

Inheritance diagram for npstat::SeriesCGF1D:

Public Member Functions
	SeriesCGF1D (const double *cumulants, unsigned nCumulants, double smin, double smax)
virtual SeriesCGF1D *	clone () const
virtual SeriesCGF1D *	shiftAndScale (double mu, double sigma) const
virtual double	smin () const
virtual double	smax () const
virtual double	derivative (unsigned order, double s) const
void	setCumulant (unsigned order, double value)
unsigned	maxOrder () const
const std::vector< double > &	allCumulants () const
bool	isConvex (double a, double b) const
SeriesCGF1D	convexify (double a, double b) const
Public Member Functions inherited from npstat::AbsCGF1D
double	operator() (double s) const
virtual double	saddlepoint (double x) const
virtual double	convexLimit (double slimit, double stepSize) const
double	standardizedCumulant (unsigned order, double s) const
double	saddlepointDensityApprox (unsigned order, double x) const
double	lugannaniRiceSFApprox (unsigned nTerms, double x) const
bool	operator== (const AbsCGF1D &r) const
bool	operator!= (const AbsCGF1D &r) const

Protected Member Functions
virtual bool	isEqual (const AbsCGF1D &r) const

Constructor & Destructor Documentation

SeriesCGF1D()

npstat::SeriesCGF1D::SeriesCGF1D	(	const double *	cumulants,
		unsigned	nCumulants,
		double	smin,
		double	smax
	)

At least the first two cumulants (mean and variance) must be provided in the "cumulants" array. cumulants[0] must contain the mean, cumulants[1] the variance, etc. "nCumulants" specifies the length of the array (and also the highest cumulant order). The variance must be positive (i.e., the degenerate distribution of a single point mass is excluded from consideration). The parameters "smin" and "smax" should be chosen in such a way that the CGF remains convex on the (smin, smax) interval.

Member Function Documentation

clone()

virtual SeriesCGF1D* npstat::SeriesCGF1D::clone ( ) const

inlinevirtual

Virtual copy constructor

Implements npstat::AbsCGF1D.

convexify()

SeriesCGF1D npstat::SeriesCGF1D::convexify	(	double	a,
		double	b
	)		const

Convexify this CFG on the given interval by adding the smallest possible higher order cumulant of the lowest even order not specified for this CGF.

derivative()

virtual double npstat::SeriesCGF1D::derivative ( unsigned  order, double  s  ) const

virtual

CGF derivatives. Get cum[order] by setting s to 0.

Implements npstat::AbsCGF1D.

isConvex()

bool npstat::SeriesCGF1D::isConvex	(	double	a,
		double	b
	)		const

Check whether the CGF is convex on the interval (a, b]. This method ignores smin and smax.

isEqual()

virtual bool npstat::SeriesCGF1D::isEqual ( const AbsCGF1D &  ) const

protectedvirtual

Comparison for equality. To be implemented by derived classes.

Implements npstat::AbsCGF1D.

shiftAndScale()

virtual SeriesCGF1D* npstat::SeriesCGF1D::shiftAndScale ( double  mu, double  sigma  ) const

virtual

CGF for the variable (X - mu)/sigma. Created on the heap and must be later deleted by the user.

Implements npstat::AbsCGF1D.

smax()

virtual double npstat::SeriesCGF1D::smax ( ) const

inlinevirtual

Supremum of the support

Implements npstat::AbsCGF1D.

smin()

virtual double npstat::SeriesCGF1D::smin ( ) const

inlinevirtual

Infimum of the support

Implements npstat::AbsCGF1D.

---

The documentation for this class was generated from the following file:

• stat/SeriesCGF1D.hh