repicea.stats.model

Class AbstractStatisticalModel<D extends StatisticalDataStructure>

java.lang.Object

repicea.stats.model.AbstractStatisticalModel<D>

Type Parameters:

D - a StatisticalDataStructure-derived class

All Implemented Interfaces:

StatisticalModel<D>

Direct Known Subclasses:

GeneralizedLinearModel, LinearModel

public abstract class AbstractStatisticalModel<D extends StatisticalDataStructure>
extends java.lang.Object
implements StatisticalModel<D>

The AbstractStatisticalModel class implements the StatisticalModel interface. It contains the basic features for a StatisticalModel, namely a data structure, a log-likelihood function and an optimizer.

Field Summary

Fields

Modifier and Type	Field and Description
protected CompositeLogLikelihood	completeLLK The complete model likelihood.

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	AbstractStatisticalModel(DataSet dataSet) Default constructor.

Method Summary

Modifier and Type	Method and Description
void	doEstimation() This method computes the parameter estimates.
CompositeLogLikelihood	getCompleteLogLikelihood() This method returns the model log-likelihood function.
double	getConvergenceCriterion() This method returns the value of the convergence criterion.
D	getDataStructure() This method returns the data structure.
protected abstract D	getDataStructureFromDataSet(DataSet dataSet) This method returns the appropriate StatisticalDataStructure from the dataSet.
Estimator	getEstimator() This method returns the optimizer of the log-likelihood function.
java.lang.String	getModelDefinition() This method returns the model definition as entered by the user.
protected java.lang.Object	getOptimizerParameters()
void	getSummary() This method returns the results of the fit on screen.
protected abstract Estimator	instantiateDefaultEstimator() This method defines the default optimizer which is to be specific to the derived classes.
protected abstract void	setCompleteLLK() This method sets the log-likelihood function of the model.
void	setConvergenceCriterion(double convergenceCriterion) This method sets the convergence criterion.
protected void	setModelDefinition(java.lang.String modelDefinition) This method sets the model definition and computes the appropriate matrix from the data.
void	setOptimizer(Estimator optimizer) This method sets the optimizer for the model.
void	setOptimizerParameters(java.lang.Object optimizerParameters) This method sets the parameter for the optimizer.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface repicea.stats.model.StatisticalModel

getParameters, getPredicted, getResiduals, setParameters

Field Detail

completeLLK

protected CompositeLogLikelihood completeLLK

The complete model likelihood.

Constructor Detail

AbstractStatisticalModel

protected AbstractStatisticalModel(DataSet dataSet)

Default constructor.

Method Detail

getDataStructureFromDataSet

protected abstract D getDataStructureFromDataSet(DataSet dataSet)

This method returns the appropriate StatisticalDataStructure from the dataSet. It is the first instruction to be called in the constructor.

Parameters:

dataSet - a DataSet instance

Returns:

a StatisticalDataStructure derived instance

getCompleteLogLikelihood

public CompositeLogLikelihood getCompleteLogLikelihood()

Description copied from interface: StatisticalModel

This method returns the model log-likelihood function.

Specified by:

getCompleteLogLikelihood in interface StatisticalModel<D extends StatisticalDataStructure>

Returns:

a LogLikelihood instance

setCompleteLLK

protected abstract void setCompleteLLK()

This method sets the log-likelihood function of the model. It is to be defined in the derived class, since the log-likelihood function depends on the different features of the model.

setOptimizer

public void setOptimizer(Estimator optimizer)

This method sets the optimizer for the model.

Parameters:

optimizer - an Optimizer instance

getEstimator

public Estimator getEstimator()

Description copied from interface: StatisticalModel

This method returns the optimizer of the log-likelihood function.

Specified by:

getEstimator in interface StatisticalModel<D extends StatisticalDataStructure>

Returns:

an Optimizer instance

getDataStructure

public D getDataStructure()

Description copied from interface: StatisticalModel

This method returns the data structure.

Specified by:

getDataStructure in interface StatisticalModel<D extends StatisticalDataStructure>

Returns:

a StatisticalDataStructure derived instance

instantiateDefaultEstimator

protected abstract Estimator instantiateDefaultEstimator()

This method defines the default optimizer which is to be specific to the derived classes.

Returns:

an Optimizer instance

setConvergenceCriterion

public void setConvergenceCriterion(double convergenceCriterion)

This method sets the convergence criterion.

Parameters:

convergenceCriterion - a double

getConvergenceCriterion

public double getConvergenceCriterion()

Description copied from interface: StatisticalModel

This method returns the value of the convergence criterion.

Specified by:

getConvergenceCriterion in interface StatisticalModel<D extends StatisticalDataStructure>

Returns:

a double

setOptimizerParameters

public void setOptimizerParameters(java.lang.Object optimizerParameters)

This method sets the parameter for the optimizer.

Parameters:

optimizerParameters -

getOptimizerParameters

protected java.lang.Object getOptimizerParameters()

doEstimation

public void doEstimation()

Description copied from interface: StatisticalModel

This method computes the parameter estimates.

Specified by:

doEstimation in interface StatisticalModel<D extends StatisticalDataStructure>

getSummary

public void getSummary()

Description copied from interface: StatisticalModel

This method returns the results of the fit on screen.

Specified by:

getSummary in interface StatisticalModel<D extends StatisticalDataStructure>

getModelDefinition

public java.lang.String getModelDefinition()

Description copied from interface: StatisticalModel

This method returns the model definition as entered by the user.

Specified by:

getModelDefinition in interface StatisticalModel<D extends StatisticalDataStructure>

Returns:

a String

setModelDefinition

protected void setModelDefinition(java.lang.String modelDefinition)
                           throws StatisticalDataException

This method sets the model definition and computes the appropriate matrix from the data.

Parameters:

modelDefinition - a String that defines the model

Throws:

StatisticalDataException