Base class for all Statistical Models. More...

#include <STK_IUnivStatModel.h>

Inheritance diagram for STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >:

Public Types
typedef ColVector::Type	Type
	Type of the data contained in the container.

typedef IRunnerUnsupervised< ColVector, WColVector >	Runner
	Type of the Runner.

Public Member Functions
virtual	~IUnivStatModel ()
	destructor

Real	computeLnLikelihood () const
	compute the log Likelihood of the statistical model.

UnivariateLaw const &	law () const

virtual int	computeNbFreeParameters () const =0
	compute the number of free parameters

virtual bool	run ()
	Estimate the parameters of the model and update the.

virtual bool	run (WColVector const &weights)
	compute the weighted empirical probability of success based on the observed variables.

Public Member Functions inherited from STK::IStatModelBase
int	nbSample () const

Real	lnNbSample () const

int	nbVariable () const

Real	lnLikelihood () const

Real	likelihood () const

int	nbFreeParameter () const

Real	computeBIC () const

Real	computeAIC () const

Real	computeML () const

Public Member Functions inherited from STK::IRunnerUnsupervised< ColVector, WColVector >
ColVector const *	p_data () const
	get the data set

virtual void	setData (ColVector const *p_data)
	Set the data set.

virtual void	setData (ColVector const &data)
	Set the data set.

Public Member Functions inherited from STK::IRunnerBase
String const &	error () const
	get the last error message.

Protected Member Functions
	IUnivStatModel ()
	default constructor.

	IUnivStatModel (ColVector const &data)
	Constructor with data set.

	IUnivStatModel (ColVector const *p_data)
	Constructor with a ptr on the data set.

	IUnivStatModel (IUnivStatModel const &model)
	Copy constructor.

virtual void	update ()
	This virtual method will be called if the user set a new data set.

virtual void	computeParameters ()=0
	compute the parameters

virtual void	computeParameters (WColVector const &weights)=0
	compute the weighted parameters

Protected Member Functions inherited from STK::IStatModelBase
	IStatModelBase ()
	Default constructor.

	IStatModelBase (int nbSample)
	Constructor with specified dimension.

	IStatModelBase (int nbSample, int nbVariable)
	Constructor with specified dimension.

	IStatModelBase (IStatModelBase const &model)
	Copy constructor.

	~IStatModelBase ()
	destructor

void	setNbFreeParameter (int const &nbFreeParameter)
	set the number of free parameters of the model

void	setNbSample (int const &nbSample)
	set the number of samples of the model

void	setNbVariable (int const &nbVariable)
	set the number of variables of the model

void	setLnLikelihood (Real const &lnLikelihood)
	set the log-likelihood of the model

void	initialize (int nbSample, int nbVariable)
	set the dimensions of the parameters of the model

Protected Member Functions inherited from STK::IRunnerUnsupervised< ColVector, WColVector >
	IRunnerUnsupervised ()
	default constructor.

	IRunnerUnsupervised (ColVector const *const p_data)
	constructor with a pointer on the constant data set

	IRunnerUnsupervised (ColVector const &data)
	constructor with a constant reference on the data set

	IRunnerUnsupervised (IRunnerUnsupervised const &runner)
	copy constructor

	~IRunnerUnsupervised ()
	destructor

Protected Member Functions inherited from STK::IRunnerBase
	IRunnerBase ()
	default constructor

	IRunnerBase (IRunnerBase const &runner)
	copy constructor

virtual	~IRunnerBase ()
	destructor

Protected Attributes
UnivariateLaw	law_
	The probability law of the model.

Protected Attributes inherited from STK::IRunnerUnsupervised< ColVector, WColVector >
ColVector const *	p_data_
	A pointer on the original data set.

Protected Attributes inherited from STK::IRunnerBase
String	msg_error_
	String with the last error message.

bool	hasRun_
	`true` if run has been used, `false` otherwise

Detailed Description

template<class ColVector, class WColVector, class UnivariateLaw>
class STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >

Base class for all Statistical Models.

A Statistical model, $\mathcal{P}$ , is a collection of probability distribution functions or probability density functions (collectively referred to as ''distributions'' for brevity). A parametric model is a collection of distributions, each of which is indexed by a unique finite-dimensional parameter: $\mathcal{P}=\{\mathbb{P}_{\theta} : \theta \in \Theta\}$ , where $\theta$ is a parameter and $\Theta \subseteq \mathbb{R}^d$ is the feasible region of parameters, which is a subset of d-dimensional Euclidean space. A statistical model may be used to describe the set of distributions from which one assumes that a particular data set is sampled. For example, if one assumes that data arise from a univariate Gaussian distribution, then one has assumed a Gaussian model: $\mathcal{P}=\{\mathbb{P}(x; \mu, \sigma) = \frac{1}{\sqrt{2 \pi} \sigma} \exp\left\{ -\frac{1}{2\sigma^2}(x-\mu)^2\right\} : \mu \in \mathbb{R}, \sigma > 0\}$ .

From a computational point of view a statistical model is defined with the help of two elements

A data set where the number of samples is the number of rows. This data set is stored in a Container of type ColVector.
A probability (density/law) which for each row of the data set can compute a density/probability.

The parameters of the distribution (if any) are directly managed by the probability law.

Further implementation of this interface have to implement the run() and the run(weights) methods in order to estimate the parameters of the univariate law.

Template Parameters

ColVector can be any kind of vector for the data set. it should at least derive from the specialization of ITContainer for Arrays::vector_,

See also: ITContainer.

Template Parameters

UnivariateLaw any probabilistic law deriving from the interface class IUnivLaw,

See also: IUnivLaw.

Definition at line 86 of file STK_IUnivStatModel.h.

Member Typedef Documentation

◆ Runner

template<class ColVector , class WColVector , class UnivariateLaw >

typedef IRunnerUnsupervised<ColVector, WColVector> STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::Runner

Type of the Runner.

Definition at line 93 of file STK_IUnivStatModel.h.

◆ Type

template<class ColVector , class WColVector , class UnivariateLaw >

typedef ColVector::Type STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::Type

Type of the data contained in the container.

Definition at line 91 of file STK_IUnivStatModel.h.

Constructor & Destructor Documentation

◆ IUnivStatModel() [1/4]

template<class ColVector , class WColVector , class UnivariateLaw >

STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::IUnivStatModel ( )

inlineprotected

default constructor.

Definition at line 97 of file STK_IUnivStatModel.h.

97: IStatModelBase(), Runner() {}

STK::IStatModelBase::IStatModelBase

IStatModelBase()

Default constructor.

Definition STK_IStatModelBase.h:59

STK::IUnivStatModel::Runner

IRunnerUnsupervised< ColVector, WColVector > Runner

Type of the Runner.

Definition STK_IUnivStatModel.h:93

◆ IUnivStatModel() [2/4]

template<class ColVector , class WColVector , class UnivariateLaw >

STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::IUnivStatModel ( ColVector const & data )

inlineprotected

Constructor with data set.

Definition at line 99 of file STK_IUnivStatModel.h.

99 : IStatModelBase(data.size(), 1), Runner(data)

100 { this->initialize(data.size(), 1);}

STK::IStatModelBase::initialize

void initialize(int nbSample, int nbVariable)

set the dimensions of the parameters of the model

Definition STK_IStatModelBase.h:132

References STK::IStatModelBase::initialize().

◆ IUnivStatModel() [3/4]

template<class ColVector , class WColVector , class UnivariateLaw >

STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::IUnivStatModel ( ColVector const * p_data )

inlineprotected

Constructor with a ptr on the data set.

Definition at line 102 of file STK_IUnivStatModel.h.

102 : IStatModelBase(), Runner(p_data)

103 { if (p_data) this->initialize(p_data->size(), 1) ;}

STK::IRunnerUnsupervised< ColVector, WColVector >::p_data

ColVector const * p_data() const

get the data set

Definition STK_IRunner.h:216

References STK::IStatModelBase::initialize(), and STK::IRunnerUnsupervised< ColVector, WColVector >::p_data().

◆ IUnivStatModel() [4/4]

template<class ColVector , class WColVector , class UnivariateLaw >

STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::IUnivStatModel ( IUnivStatModel< ColVector, WColVector, UnivariateLaw > const & model )

inlineprotected

Copy constructor.

Definition at line 105 of file STK_IUnivStatModel.h.

106 : IStatModelBase(model), Runner(model), law_(model.law_) {}

STK::IUnivStatModel::law_

UnivariateLaw law_

The probability law of the model.

Definition STK_IUnivStatModel.h:174

◆ ~IUnivStatModel()

template<class ColVector , class WColVector , class UnivariateLaw >

virtual STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::~IUnivStatModel ( )

inlinevirtual

destructor

Definition at line 110 of file STK_IUnivStatModel.h.

110{}

Member Function Documentation

◆ computeLnLikelihood()

template<class ColVector , class WColVector , class UnivariateLaw >

Real STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeLnLikelihood ( ) const

inline

compute the log Likelihood of the statistical model.

Definition at line 112 of file STK_IUnivStatModel.h.

    {
      Real sum = 0.0;
      for (int i= p_data()->begin(); i<= p_data()->lastIdx(); i++)
      { if (!Arithmetic<Type>::isNA(p_data()->elt(i))) sum += law_.lpdf(p_data()->elt(i));}
      return sum;
    }

References STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::law_, STK::IRunnerUnsupervised< ColVector, WColVector >::p_data(), and STK::sum().

Referenced by STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run(), and STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run().

◆ computeNbFreeParameters()

template<class ColVector , class WColVector , class UnivariateLaw >

virtual int STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeNbFreeParameters ( ) const

pure virtual

compute the number of free parameters

Implemented in STK::BernoulliModel< Array, WColVector >.

Referenced by STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run(), and STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run().

◆ computeParameters() [1/2]

template<class ColVector , class WColVector , class UnivariateLaw >

virtual void STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeParameters ( )

protectedpure virtual

compute the parameters

Implemented in STK::BernoulliModel< Array, WColVector >.

Referenced by STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run(), and STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run().

◆ computeParameters() [2/2]

template<class ColVector , class WColVector , class UnivariateLaw >

virtual void STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeParameters ( WColVector const & weights )

protectedpure virtual

compute the weighted parameters

Implemented in STK::BernoulliModel< Array, WColVector >.

◆ law()

template<class ColVector , class WColVector , class UnivariateLaw >

UnivariateLaw const & STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::law ( ) const

inline

Returns: the total available observations

Definition at line 120 of file STK_IUnivStatModel.h.

120{ return law_;}

References STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::law_.

◆ run() [1/2]

template<class ColVector , class WColVector , class UnivariateLaw >

virtual bool STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run ( )

inlinevirtual

Estimate the parameters of the model and update the.

Implements STK::IRunnerUnsupervised< ColVector, WColVector >.

Definition at line 125 of file STK_IUnivStatModel.h.

    {
      if (!p_data())
      { this->msg_error_ = STKERROR_NO_ARG(IUnivStatModel::run(),data have not be set);
        return false;
      }
      try
      {
        // compute weighted parameters
        computeParameters();
        // compute log-likelihood
        this->setLnLikelihood(computeLnLikelihood());
        // set the number of free parameters
        this->setNbFreeParameter(computeNbFreeParameters());
      }
      catch (Exception const& e)
      { this->msg_error_ = e.error(); return false;}
      return true;
    }

References STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeLnLikelihood(), STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeNbFreeParameters(), STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeParameters(), STK::Exception::error(), STK::IRunnerBase::msg_error_, STK::IRunnerUnsupervised< ColVector, WColVector >::p_data(), STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run(), STK::IStatModelBase::setLnLikelihood(), STK::IStatModelBase::setNbFreeParameter(), and STKERROR_NO_ARG.

Referenced by STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run(), and STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run().

◆ run() [2/2]

template<class ColVector , class WColVector , class UnivariateLaw >

virtual bool STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run ( WColVector const & weights )

inlinevirtual

compute the weighted empirical probability of success based on the observed variables.

The NA values are discarded.

Parameters

weights the weights of the observations

Implements STK::IRunnerUnsupervised< ColVector, WColVector >.

Definition at line 148 of file STK_IUnivStatModel.h.

    {
      if (!p_data())
      { this->msg_error_ = STKERROR_NO_ARG(IUnivStatModel::run(weights),data have not be set);
        return false;
      }
      try
      {
        // compute weighted parameters
        computeParameters(weights);
        // compute log-likelihood
        this->setLnLikelihood(computeLnLikelihood());
        // set the number of free parameters
        this->setNbFreeParameter(computeNbFreeParameters());
      }
      catch (Exception const& e)
      { this->msg_error_ = e.error(); return false;}
      return true;
    }

References STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeLnLikelihood(), STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeNbFreeParameters(), STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeParameters(), STK::Exception::error(), STK::IRunnerBase::msg_error_, STK::IRunnerUnsupervised< ColVector, WColVector >::p_data(), STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::run(), STK::IStatModelBase::setLnLikelihood(), STK::IStatModelBase::setNbFreeParameter(), and STKERROR_NO_ARG.

◆ update()

template<class ColVector , class WColVector , class UnivariateLaw >

virtual void STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::update ( )

inlineprotectedvirtual

This virtual method will be called if the user set a new data set.

See also: IRunnerUnsupervised::setData

Reimplemented from STK::IRunnerBase.

Definition at line 171 of file STK_IUnivStatModel.h.

172 { if (p_data()) this->initialize(p_data()->size(), 1); }

References STK::IStatModelBase::initialize(), and STK::IRunnerUnsupervised< ColVector, WColVector >::p_data().

Member Data Documentation

◆ law_

template<class ColVector , class WColVector , class UnivariateLaw >

UnivariateLaw STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::law_

protected

The probability law of the model.

Definition at line 174 of file STK_IUnivStatModel.h.

Referenced by STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::computeLnLikelihood(), and STK::IUnivStatModel< ColVector, WColVector, UnivariateLaw >::law().

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

STK_IUnivStatModel.h

Public Types

Public Member Functions

Protected Member Functions

Protected Attributes

Detailed Description

Member Typedef Documentation

◆ Runner

◆ Type

Constructor & Destructor Documentation

◆ IUnivStatModel() [1/4]

◆ IUnivStatModel() [2/4]

◆ IUnivStatModel() [3/4]

◆ IUnivStatModel() [4/4]

◆ ~IUnivStatModel()

Member Function Documentation

◆ computeLnLikelihood()

◆ computeNbFreeParameters()

◆ computeParameters() [1/2]

◆ computeParameters() [2/2]

◆ law()

◆ run() [1/2]

◆ run() [2/2]

◆ update()

Member Data Documentation

◆ law_