vtkDescriptiveStatistics Class Reference

#include <vtkDescriptiveStatistics.h>

Inheritance diagram for vtkDescriptiveStatistics:

[legend]

Collaboration diagram for vtkDescriptiveStatistics:

[legend]

List of all members.

Detailed Description

A class for univariate descriptive statistics.

Private implementation for bivariate statistics algorithms.

Given a selection of columns of interest in an input data table, this class provides the following functionalities, depending on the chosen execution options: Learn: calculate extremal values, sample mean, and M2, M3, and M4 aggregates (cf. P. Pebay, Formulas for robust, one-pass parallel computation of covariances and Arbitrary-Order Statistical Moments, Sandia Report SAND2008-6212, Sep 2008, http://infoserve.sandia.gov/sand_doc/2008/086212.pdf for details) Derive: calculate unbiased variance estimator, standard deviation estimator, two skewness estimators, and two kurtosis excess estimators. Assess: given an input data set, a reference value and a non-negative deviation, mark each datum with corresponding relative deviation (1-dimensional Mahlanobis distance). If the deviation is zero, then mark each datum which are equal to the reference value with 0, and all others with 1. By default, the reference value and the deviation are, respectively, the mean and the standard deviation of the input model. Test: calculate Jarque-Bera statistic and, if VTK to R interface is available, retrieve corresponding p-value for normality testing.

Thanks:: Thanks to Philippe Pebay and David Thompson from Sandia National Laboratories for implementing this class.

Examples:: vtkDescriptiveStatistics (Examples)

Tests:: vtkDescriptiveStatistics (Tests)

The main purpose of this class is to avoid exposure of STL container through the APIs of the vtkStatistics classes APIs

Thanks:: Thanks to Philippe Pebay and David Thompson from Sandia National Laboratories for implementing this class.

Definition at line 63 of file vtkDescriptiveStatistics.h.


Public Types
typedef vtkUnivariateStatisticsAlgorithm	Superclass
Public Member Functions
virtual const char *	GetClassName ()
virtual int	IsA (const char *type)
void	PrintSelf (ostream &os, vtkIndent indent)
void	SetNominalParameter (const char *name)
void	SetDeviationParameter (const char *name)

virtual void	SetUnbiasedVariance (int)
virtual int	GetUnbiasedVariance ()
virtual void	UnbiasedVarianceOn ()
virtual void	UnbiasedVarianceOff ()

virtual void	SetG1Skewness (int)
virtual int	GetG1Skewness ()
virtual void	G1SkewnessOn ()
virtual void	G1SkewnessOff ()

virtual void	SetG2Kurtosis (int)
virtual int	GetG2Kurtosis ()
virtual void	G2KurtosisOn ()
virtual void	G2KurtosisOff ()

virtual void	SetSignedDeviations (int)
virtual int	GetSignedDeviations ()
virtual void	SignedDeviationsOn ()
virtual void	SignedDeviationsOff ()

virtual void	Aggregate (vtkDataObjectCollection , vtkMultiBlockDataSet )
Static Public Member Functions
static int	IsTypeOf (const char *type)
static vtkDescriptiveStatistics *	SafeDownCast (vtkObject *o)
static vtkDescriptiveStatistics *	New ()
Protected Member Functions
	vtkDescriptiveStatistics ()
	~vtkDescriptiveStatistics ()
virtual void	Derive (vtkMultiBlockDataSet *)

virtual void	Learn (vtkTable inData, vtkTable inParameters, vtkMultiBlockDataSet *outMeta)

virtual void	Test (vtkTable inData, vtkMultiBlockDataSet inMeta, vtkTable *outMeta)

virtual void	SelectAssessFunctor (vtkTable outData, vtkDataObject inMeta, vtkStringArray rowNames, AssessFunctor &dfunc)
Protected Attributes
int	UnbiasedVariance
int	G1Skewness
int	G2Kurtosis
int	SignedDeviations

Member Typedef Documentation

typedef vtkUnivariateStatisticsAlgorithm vtkDescriptiveStatistics::Superclass

Reimplemented from vtkUnivariateStatisticsAlgorithm.

Reimplemented in vtkPDescriptiveStatistics.

Definition at line 66 of file vtkDescriptiveStatistics.h.

Constructor & Destructor Documentation

vtkDescriptiveStatistics::vtkDescriptiveStatistics ( ) [protected]

vtkDescriptiveStatistics::~vtkDescriptiveStatistics ( ) [protected]

Member Function Documentation

virtual const char* vtkDescriptiveStatistics::GetClassName ( ) [virtual]

Reimplemented from vtkUnivariateStatisticsAlgorithm.

Reimplemented in vtkPDescriptiveStatistics.

static int vtkDescriptiveStatistics::IsTypeOf ( const char * name ) [static]

Return 1 if this class type is the same type of (or a subclass of) the named class. Returns 0 otherwise. This method works in combination with vtkTypeMacro found in vtkSetGet.h.

Reimplemented from vtkUnivariateStatisticsAlgorithm.

Reimplemented in vtkPDescriptiveStatistics.

virtual int vtkDescriptiveStatistics::IsA ( const char * name ) [virtual]

Return 1 if this class is the same type of (or a subclass of) the named class. Returns 0 otherwise. This method works in combination with vtkTypeMacro found in vtkSetGet.h.

Reimplemented from vtkUnivariateStatisticsAlgorithm.

Reimplemented in vtkPDescriptiveStatistics.

static vtkDescriptiveStatistics* vtkDescriptiveStatistics::SafeDownCast ( vtkObject * o ) [static]

Reimplemented from vtkUnivariateStatisticsAlgorithm.

Reimplemented in vtkPDescriptiveStatistics.

void vtkDescriptiveStatistics::PrintSelf	(	ostream &	os,
		vtkIndent	indent
	)			`[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 vtkUnivariateStatisticsAlgorithm.

Reimplemented in vtkPDescriptiveStatistics.

static vtkDescriptiveStatistics* vtkDescriptiveStatistics::New ( ) [static]

Create an object with Debug turned off, modified time initialized to zero, and reference counting on.

Reimplemented from vtkTableAlgorithm.

Reimplemented in vtkPDescriptiveStatistics.

virtual void vtkDescriptiveStatistics::SetUnbiasedVariance ( int ) [virtual]

Set/get whether the unbiased estimator for the variance should be used, or if the population variance will be calculated. The default is that the unbiased estimator will be used.

virtual int vtkDescriptiveStatistics::GetUnbiasedVariance ( ) [virtual]

Set/get whether the unbiased estimator for the variance should be used, or if the population variance will be calculated. The default is that the unbiased estimator will be used.

virtual void vtkDescriptiveStatistics::UnbiasedVarianceOn ( ) [virtual]

Set/get whether the unbiased estimator for the variance should be used, or if the population variance will be calculated. The default is that the unbiased estimator will be used.

virtual void vtkDescriptiveStatistics::UnbiasedVarianceOff ( ) [virtual]

Set/get whether the unbiased estimator for the variance should be used, or if the population variance will be calculated. The default is that the unbiased estimator will be used.

virtual void vtkDescriptiveStatistics::SetG1Skewness ( int ) [virtual]

Set/get whether the G1 estimator for the skewness should be used, or if the g1 skewness will be calculated. The default is that the g1 skewness estimator will be used.

virtual int vtkDescriptiveStatistics::GetG1Skewness ( ) [virtual]

Set/get whether the G1 estimator for the skewness should be used, or if the g1 skewness will be calculated. The default is that the g1 skewness estimator will be used.

virtual void vtkDescriptiveStatistics::G1SkewnessOn ( ) [virtual]

Set/get whether the G1 estimator for the skewness should be used, or if the g1 skewness will be calculated. The default is that the g1 skewness estimator will be used.

virtual void vtkDescriptiveStatistics::G1SkewnessOff ( ) [virtual]

Set/get whether the G1 estimator for the skewness should be used, or if the g1 skewness will be calculated. The default is that the g1 skewness estimator will be used.

virtual void vtkDescriptiveStatistics::SetG2Kurtosis ( int ) [virtual]

Set/get whether the G2 estimator for the kurtosis should be used, or if the g2 kurtosis will be calculated. The default is that the g2 kurtosis estimator will be used.

virtual int vtkDescriptiveStatistics::GetG2Kurtosis ( ) [virtual]

Set/get whether the G2 estimator for the kurtosis should be used, or if the g2 kurtosis will be calculated. The default is that the g2 kurtosis estimator will be used.

virtual void vtkDescriptiveStatistics::G2KurtosisOn ( ) [virtual]

Set/get whether the G2 estimator for the kurtosis should be used, or if the g2 kurtosis will be calculated. The default is that the g2 kurtosis estimator will be used.

virtual void vtkDescriptiveStatistics::G2KurtosisOff ( ) [virtual]

Set/get whether the G2 estimator for the kurtosis should be used, or if the g2 kurtosis will be calculated. The default is that the g2 kurtosis estimator will be used.

virtual void vtkDescriptiveStatistics::SetSignedDeviations ( int ) [virtual]

Set/get whether the deviations returned should be signed, or should only have their magnitude reported. The default is that signed deviations will be computed.

virtual int vtkDescriptiveStatistics::GetSignedDeviations ( ) [virtual]

Set/get whether the deviations returned should be signed, or should only have their magnitude reported. The default is that signed deviations will be computed.

virtual void vtkDescriptiveStatistics::SignedDeviationsOn ( ) [virtual]

Set/get whether the deviations returned should be signed, or should only have their magnitude reported. The default is that signed deviations will be computed.

virtual void vtkDescriptiveStatistics::SignedDeviationsOff ( ) [virtual]

Set/get whether the deviations returned should be signed, or should only have their magnitude reported. The default is that signed deviations will be computed.

void vtkDescriptiveStatistics::SetNominalParameter ( const char * name )

A convenience method (in particular for UI wrapping) to set the name of the column that contains the nominal value for the Assess option.

void vtkDescriptiveStatistics::SetDeviationParameter ( const char * name )

A convenience method (in particular for UI wrapping) to set the name of the column that contains the deviation for the Assess option.

virtual void vtkDescriptiveStatistics::Aggregate	(	vtkDataObjectCollection *	,
		vtkMultiBlockDataSet *
	)			`[virtual]`

Given a collection of models, calculate aggregate model

Implements vtkStatisticsAlgorithm.

virtual void vtkDescriptiveStatistics::Learn	(	vtkTable *	inData,
		vtkTable *	inParameters,
		vtkMultiBlockDataSet *	outMeta
	)			`[protected, virtual]`

Execute the calculations required by the Learn option, given some input Data NB: input parameters are unused.

Implements vtkStatisticsAlgorithm.

Reimplemented in vtkPDescriptiveStatistics.

virtual void vtkDescriptiveStatistics::Derive ( vtkMultiBlockDataSet * ) [protected, virtual]

Execute the calculations required by the Derive option.

Implements vtkStatisticsAlgorithm.

virtual void vtkDescriptiveStatistics::Test	(	vtkTable *	inData,
		vtkMultiBlockDataSet *	inMeta,
		vtkTable *	outMeta
	)			`[protected, virtual]`

Execute the calculations required by the Test option.

Implements vtkStatisticsAlgorithm.

virtual void vtkDescriptiveStatistics::SelectAssessFunctor	(	vtkTable *	outData,
		vtkDataObject *	inMeta,
		vtkStringArray *	rowNames,
		AssessFunctor *&	dfunc
	)			`[protected, virtual]`