npstat::EllipticalDistribution Class Reference

Inheritance diagram for npstat::EllipticalDistribution:

Public Member Functions
	EllipticalDistribution (const double *location, unsigned dim, const Matrix< double > &transformationMatrix, const AbsDistribution1D &gDistro, const AbsDistribution1D &hDistro)
	EllipticalDistribution (const EllipticalDistribution &)
EllipticalDistribution &	operator= (const EllipticalDistribution &)
virtual EllipticalDistribution *	clone () const
virtual double	density (const double *x, unsigned dim) const
virtual void	unitMap (const double *rnd, unsigned bufLen, double *x) const
virtual bool	mappedByQuantiles () const
virtual unsigned	random (AbsRandomGenerator &g, double *x, unsigned lenX) const
double	chiSquare (const double *x, unsigned dim) const
const AbsDistribution1D &	getGDistro () const
const AbsDistribution1D &	getHDistro () const
const Matrix< double > &	getTransformationMatrix () const
const std::vector< double > &	getShift () const
virtual gs::ClassId	classId () const
virtual bool	write (std::ostream &os) const
Public Member Functions inherited from npstat::AbsDistributionND
	AbsDistributionND (const unsigned dim)
	AbsDistributionND (const AbsDistributionND &r)
AbsDistributionND &	operator= (const AbsDistributionND &r)
bool	operator== (const AbsDistributionND &r) const
bool	operator!= (const AbsDistributionND &r) const
unsigned	dim () const

Static Public Member Functions
static const char *	classname ()
static unsigned	version ()
static EllipticalDistribution *	read (const gs::ClassId &id, std::istream &in)
Static Public Member Functions inherited from npstat::AbsDistributionND
static const char *	classname ()
static unsigned	version ()
static AbsDistributionND *	read (const gs::ClassId &id, std::istream &)

Protected Member Functions
virtual bool	isEqual (const AbsDistributionND &) const

Protected Attributes
std::vector< double >	mu_
Matrix< double >	A_
Matrix< double >	InvCovmat_
AbsDistribution1D *	g_
AbsDistribution1D *	h_
double	det_
double	gNorm_
Protected Attributes inherited from npstat::AbsDistributionND
const unsigned	dim_

Constructor & Destructor Documentation

EllipticalDistribution()

npstat::EllipticalDistribution::EllipticalDistribution	(	const double *	location,
		unsigned	dim,
		const Matrix< double > &	transformationMatrix,
		const AbsDistribution1D &	gDistro,
		const AbsDistribution1D &	hDistro
	)

The constructor arguments are as follows:

location, dim The shift and the dimensionality of the distribution. The array "location" must have at least "dim" elements.

transformationMatrix The square matrix for generating random variables from this density according to x = location + transformationMatrix*y, where y is a spherically distributed random variable. For multivariate normal, transformationMatrix is the square root of the covariance matrix.

gDistro The "generator" distribution. The multivariate density is going to be proportional to gDistro.density(chi-square), where chi-square variable is constructed as in the multivariate normal. Must have gDistro.quantile(0.0) = 0.0.

hDistro Distribution of the r^2 variable. Must have hDistro.quantile(0.0) = 0.0.

Member Function Documentation

chiSquare()

double npstat::EllipticalDistribution::chiSquare	(	const double *	x,
		unsigned	dim
	)		const

This function returns the value of the quadratic form

classId()

virtual gs::ClassId npstat::EllipticalDistribution::classId ( ) const

inlinevirtual

Prototype needed for I/O

Implements npstat::AbsDistributionND.

Reimplemented in npstat::EllipticalPearsonTypeII, npstat::EllipticalPearsonTypeVII, npstat::EllipticalKotz, and npstat::EllipticalNormal.

clone()

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

inlinevirtual

"Virtual copy constructor"

Implements npstat::AbsDistributionND.

density()

virtual double npstat::EllipticalDistribution::density ( const double *  x, unsigned  dim  ) const

virtual

Probability density

Implements npstat::AbsDistributionND.

Reimplemented in npstat::EllipticalKotz.

mappedByQuantiles()

virtual bool npstat::EllipticalDistribution::mappedByQuantiles ( ) const

inlinevirtual

The following method should return "true" in case the "unitMap" method is implemented by a sequence of conditional quantile functions. Distributions with such maps permit quantile-based interpolation procedures.

Implements npstat::AbsDistributionND.

random()

virtual unsigned npstat::EllipticalDistribution::random ( AbsRandomGenerator &  g, double *  x, unsigned  lenX  ) const

virtual

Random number generator according to the given distribution. Should return the number of random points used up from the generator. Length of the provided buffer "x" should be equal to the function dimensionality.

Reimplemented from npstat::AbsDistributionND.

unitMap()

virtual void npstat::EllipticalDistribution::unitMap ( const double *  rnd, unsigned  bufLen, double *  x  ) const

virtual

Mapping from the unit hypercube into the density support region. Note that "bufLen" does not have to be equal to the dimensionality of the function. There may be an efficient way to generate just the leading dimensions in case "bufLen" is smaller than the dimensionality.

Implements npstat::AbsDistributionND.

---

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

• stat/EllipticalDistribution.hh