ITK  4.1.0
Insight Segmentation and Registration Toolkit
Public Types | Public Member Functions | Protected Member Functions | Protected Attributes | Private Member Functions
itk::Statistics::ProbabilityDistribution Class Reference

#include <itkProbabilityDistribution.h>

+ Inheritance diagram for itk::Statistics::ProbabilityDistribution:
+ Collaboration diagram for itk::Statistics::ProbabilityDistribution:

List of all members.

Public Types

typedef SmartPointer< const SelfConstPointer
typedef Array< double > ParametersType
typedef SmartPointer< SelfPointer
typedef ProbabilityDistribution Self
typedef Object Superclass

Public Member Functions

virtual double EvaluateCDF (double x) const =0
virtual double EvaluateCDF (double x, const ParametersType &) const =0
virtual double EvaluateInverseCDF (double p) const =0
virtual double EvaluateInverseCDF (double p, const ParametersType &) const =0
virtual double EvaluatePDF (double x) const =0
virtual double EvaluatePDF (double x, const ParametersType &) const =0
virtual double GetMean () const =0
virtual const char * GetNameOfClass () const
virtual SizeValueType GetNumberOfParameters () const =0
virtual const ParametersTypeGetParameters ()
virtual double GetVariance () const =0
virtual bool HasMean () const =0
virtual bool HasVariance () const =0
virtual void SetParameters (const ParametersType &params)

Protected Member Functions

void PrintSelf (std::ostream &os, Indent indent) const
 ProbabilityDistribution (void)
virtual ~ProbabilityDistribution (void)

Protected Attributes

ParametersType m_Parameters

Private Member Functions

void operator= (const Self &)
 ProbabilityDistribution (const Self &)

Detailed Description

ProbabilityDistribution class defines common interface for statistical distributions (pdfs, cdfs, etc.).

ProbabilityDistribution defines a common interface for parameteric and non-parametric distributions. ProbabilityDistribution provides access to the probability density function (pdf), the cumulative distribution function (cdf), and the inverse cumulative distribution function.

ProbabilityDistribution also defines an abstract interface for setting parameters of distribution (mean/variance for a Gaussian, degrees of freedom for Student-t, etc.).

Note that nonparametric subclasses of ProbabilityDistribution are possible. For instance, a nonparametric implementation may use a histogram or kernel density function to model the distribution.

The EvaluatePDF(), EvaluateCDF, EvaluateInverseCDF() methods are all virtual, allowing algorithms to be written with an abstract interface to a distribution (with said distribution provided to the algorithm at run-time). Static methods, not requiring an instance of the distribution, are also allowed. The static methods allow for optimized access to distributions when the distribution is known a priori to the algorithm.

ProbabilityDistributions are univariate. Multivariate versions may be provided under a separate superclass (since the parameters to the pdf and cdf would have to be vectors not scalars). Perhaps this class will be named MultivariateProbabilityDistribution.

ProbabilityDistributions can be used for standard statistical tests: Z-scores, t-tests, chi-squared tests, F-tests, etc.

Note:
This work is part of the National Alliance for Medical Image Computing (NAMIC), funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant U54 EB005149. Information on the National Centers for Biomedical Computing can be obtained from http://commonfund.nih.gov/bioinformatics.

Definition at line 71 of file itkProbabilityDistribution.h.


Member Typedef Documentation

Type of the parameter vector.

Definition at line 82 of file itkProbabilityDistribution.h.

Standard class typedefs

Reimplemented from itk::Object.

Reimplemented in itk::Statistics::GaussianDistribution, itk::Statistics::ChiSquareDistribution, and itk::Statistics::TDistribution.

Definition at line 76 of file itkProbabilityDistribution.h.


Constructor & Destructor Documentation

Definition at line 157 of file itkProbabilityDistribution.h.

virtual itk::Statistics::ProbabilityDistribution::~ProbabilityDistribution ( void  ) [inline, protected, virtual]

Definition at line 158 of file itkProbabilityDistribution.h.


Member Function Documentation

virtual double itk::Statistics::ProbabilityDistribution::EvaluateCDF ( double  x) const [pure virtual]

Evaluate the cumulative distribution function (cdf). The parameters of the distribution are assigned via SetParameters(). See concrete subclasses for the ordering of parameters.

Implemented in itk::Statistics::GaussianDistribution, itk::Statistics::ChiSquareDistribution, and itk::Statistics::TDistribution.

virtual double itk::Statistics::ProbabilityDistribution::EvaluateCDF ( double  x,
const ParametersType  
) const [pure virtual]

Evaluate the cumulative distribution function (cdf). The parameters for the distribution are passed as a parameters vector. See concrete subclasses for the ordering of parameters.

Implemented in itk::Statistics::GaussianDistribution, itk::Statistics::ChiSquareDistribution, and itk::Statistics::TDistribution.

virtual double itk::Statistics::ProbabilityDistribution::EvaluateInverseCDF ( double  p) const [pure virtual]

Evaluate the inverse cumulative distribution function (inverse cdf). Parameter p must be between 0.0 and 1.0. The parameters of the distribution are assigned via SetParameters(). See concrete subclasses for the ordering of parameters.

Implemented in itk::Statistics::GaussianDistribution, itk::Statistics::ChiSquareDistribution, and itk::Statistics::TDistribution.

virtual double itk::Statistics::ProbabilityDistribution::EvaluateInverseCDF ( double  p,
const ParametersType  
) const [pure virtual]

Evaluate the inverse cumulative distribution function (inverse cdf). Parameter p must be between 0.0 and 1.0. The parameters for the distribution are passed as a parameters vector. See concrete subclasses for the ordering of parameters.

Implemented in itk::Statistics::GaussianDistribution, itk::Statistics::ChiSquareDistribution, and itk::Statistics::TDistribution.

virtual double itk::Statistics::ProbabilityDistribution::EvaluatePDF ( double  x) const [pure virtual]

Evaluate the probability density function (pdf). The parameters of the distribution are assigned via SetParameters().

Implemented in itk::Statistics::GaussianDistribution, itk::Statistics::ChiSquareDistribution, and itk::Statistics::TDistribution.

virtual double itk::Statistics::ProbabilityDistribution::EvaluatePDF ( double  x,
const ParametersType  
) const [pure virtual]

Evaluate the probability density function (pdf). The parameters for the distribution are passed as a parameters vector. See concrete subclasses for the ordering of parameters.

Implemented in itk::Statistics::GaussianDistribution, itk::Statistics::ChiSquareDistribution, and itk::Statistics::TDistribution.

virtual double itk::Statistics::ProbabilityDistribution::GetMean ( ) const [pure virtual]

Get the mean of the distribution. If the mean does not exist, then quiet_NaN may is returned.

Implemented in itk::Statistics::ChiSquareDistribution, itk::Statistics::TDistribution, and itk::Statistics::GaussianDistribution.

virtual const char* itk::Statistics::ProbabilityDistribution::GetNameOfClass ( ) const [virtual]

Return the number of parameters that describe the distribution. For nonparametric distributions, this will be a function of the number of samples.

Implemented in itk::Statistics::GaussianDistribution, itk::Statistics::ChiSquareDistribution, and itk::Statistics::TDistribution.

Get the parameters of the distribution. See concrete subclasses for the order of parameters. Subclasses may provide convenience methods for setting parameters, i.e. SetDegreesOfFreedom(), etc.

virtual double itk::Statistics::ProbabilityDistribution::GetVariance ( ) const [pure virtual]

Get the variance of the distribution. If the variance does not exist, then quiet_NaN is returned.

Implemented in itk::Statistics::GaussianDistribution, itk::Statistics::TDistribution, and itk::Statistics::ChiSquareDistribution.

virtual bool itk::Statistics::ProbabilityDistribution::HasMean ( ) const [pure virtual]
virtual bool itk::Statistics::ProbabilityDistribution::HasVariance ( ) const [pure virtual]
void itk::Statistics::ProbabilityDistribution::operator= ( const Self ) [private]

Mutex lock to protect modification to the reference count

Reimplemented from itk::Object.

Reimplemented in itk::Statistics::GaussianDistribution, itk::Statistics::TDistribution, and itk::Statistics::ChiSquareDistribution.

void itk::Statistics::ProbabilityDistribution::PrintSelf ( std::ostream &  os,
Indent  indent 
) const [inline, protected, virtual]

Methods invoked by Print() to print information about the object including superclasses. Typically not called by the user (use Print() instead) but used in the hierarchical print process to combine the output of several classes.

Reimplemented from itk::Object.

Reimplemented in itk::Statistics::GaussianDistribution, itk::Statistics::TDistribution, and itk::Statistics::ChiSquareDistribution.

Definition at line 159 of file itkProbabilityDistribution.h.

virtual void itk::Statistics::ProbabilityDistribution::SetParameters ( const ParametersType params) [inline, virtual]

Set the parameters of the distribution. See concrete subclasses for the order of the parameters. Subclasses may provide convenience methods for setting parameters, i.e. SetDegreesOfFreedom(), etc.

Definition at line 100 of file itkProbabilityDistribution.h.

References itk::Array< TValueType >::GetSize().


Member Data Documentation

Definition at line 165 of file itkProbabilityDistribution.h.


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