repicea.stats.model.glm.copula

Class FGMCopulaGLModel

java.lang.Object

repicea.stats.model.AbstractStatisticalModel<HierarchicalStatisticalDataStructure>

repicea.stats.model.glm.GeneralizedLinearModel

repicea.stats.model.glm.copula.FGMCopulaGLModel

All Implemented Interfaces:

StatisticalModel<HierarchicalStatisticalDataStructure>

public class FGMCopulaGLModel
extends GeneralizedLinearModel

The FGMCopulaGLModel class implements a Farlie-Gumbel-Morgenstein (FGM) copula for binary outcomes. The method is described in Bhat and Sener 2009.

See Also:

Bhat, C.R., and Sener, I. N. 2009. A copula-based closed form binary logit choice model for accomodating spatial correlation across observational units. Journal of Geographical Systems 11(3): 243-272.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
protected static class	FGMCopulaGLModel.LikelihoodValue

Field Summary

Fields inherited from class repicea.stats.model.glm.GeneralizedLinearModel

individualLLK, linkFunctionType, matrixX, y

Fields inherited from class repicea.stats.model.AbstractStatisticalModel

completeLLK

Constructor Summary

Constructors

Constructor and Description
FGMCopulaGLModel(GeneralizedLinearModel glm, CopulaExpression copula) Constructor for this class

Method Summary

Modifier and Type	Method and Description
protected CopulaExpression	getCopula()
HierarchicalStatisticalDataStructure	getDataStructure() This method returns the data structure.
protected HierarchicalStatisticalDataStructure	getDataStructureFromDataSet(DataSet dataSet) This method returns the appropriate StatisticalDataStructure from the dataSet.
Matrix	getParameters()
void	getSummary() This method returns the results of the fit on screen.
void	gridSearch(int parameterName, double start, double end, double step) This method scans the log likelihood function within a range of values for a particular parameter.
protected void	setCompleteLLK() This method sets the log-likelihood function of the model.
void	setParameters(Matrix beta)
java.lang.String	toString()

Methods inherited from class repicea.stats.model.glm.GeneralizedLinearModel

getLinearPredictions, getLinkFunctionType, getPredicted, getResiduals, initializeLinkFunction, instantiateDefaultEstimator, setModelDefinition

Methods inherited from class repicea.stats.model.AbstractStatisticalModel

doEstimation, getCompleteLogLikelihood, getConvergenceCriterion, getEstimator, getModelDefinition, getOptimizerParameters, setConvergenceCriterion, setOptimizer, setOptimizerParameters

Methods inherited from class java.lang.Object

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

Constructor Detail

FGMCopulaGLModel

public FGMCopulaGLModel(GeneralizedLinearModel glm,
                        CopulaExpression copula)
                 throws StatisticalDataException

Constructor for this class

Parameters:

glm - a GeneralizedLinearModel instance

copula - a CopulaExpression instance

Throws:

StatisticalDataException - if the hierarchical level specification in the copula is not found in the data set

Method Detail

getParameters

public Matrix getParameters()

Specified by:

getParameters in interface StatisticalModel<HierarchicalStatisticalDataStructure>

Overrides:

getParameters in class GeneralizedLinearModel

setParameters

public void setParameters(Matrix beta)

Specified by:

setParameters in interface StatisticalModel<HierarchicalStatisticalDataStructure>

Overrides:

setParameters in class GeneralizedLinearModel

gridSearch

public void gridSearch(int parameterName,
                       double start,
                       double end,
                       double step)

This method scans the log likelihood function within a range of values for a particular parameter.

Parameters:

parameterName - the index of the parameter

start - the starting value

end - the ending value

step - the step between these two values.

setCompleteLLK

protected void setCompleteLLK()

Description copied from class: AbstractStatisticalModel

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.

Overrides:

setCompleteLLK in class GeneralizedLinearModel

toString

public java.lang.String toString()

Overrides:

toString in class GeneralizedLinearModel

getDataStructure

public HierarchicalStatisticalDataStructure getDataStructure()

Description copied from interface: StatisticalModel

This method returns the data structure.

Specified by:

getDataStructure in interface StatisticalModel<HierarchicalStatisticalDataStructure>

Overrides:

getDataStructure in class AbstractStatisticalModel<HierarchicalStatisticalDataStructure>

Returns:

a StatisticalDataStructure derived instance

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<HierarchicalStatisticalDataStructure>

Overrides:

getSummary in class AbstractStatisticalModel<HierarchicalStatisticalDataStructure>

getCopula

protected CopulaExpression getCopula()

getDataStructureFromDataSet

protected HierarchicalStatisticalDataStructure getDataStructureFromDataSet(DataSet dataSet)

Description copied from class: AbstractStatisticalModel

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

Overrides:

getDataStructureFromDataSet in class GeneralizedLinearModel

Parameters:

dataSet - a DataSet instance

Returns:

a StatisticalDataStructure derived instance