Package com.bayesserver.analysis

Class SensitivityToParameters

java.lang.Object

com.bayesserver.analysis.SensitivityToParameters

public final class SensitivityToParameters
extends Object

Calculates the affect of one or more parameters on the value of a hypothesis.

Constructor Summary

Constructors

Constructor	Description
SensitivityToParameters(Network network, InferenceFactory factory)	Initializes a new instance of the SensitivityToParameters class .

Method Summary

Modifier and Type	Method	Description
SensitivityFunctionOneWay	oneWay(Evidence evidence, State hypothesis, ParameterReference parameter)	Calculates how a hypothesis varies based on changes to a single parameter.
SensitivityFunctionTwoWay	twoWay(Evidence evidence, State hypothesis, ParameterReference parameter1, ParameterReference parameter2)	Calculates how a hypothesis varies based on changes to two parameters.

Methods inherited from class java.lang.Object

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

Constructor Detail

SensitivityToParameters

public SensitivityToParameters(Network network,
                               InferenceFactory factory)

Initializes a new instance of the SensitivityToParameters class .

Parameters:

network - The network.

factory - The inference factory which will be used to create inference engines during an analysis.

Method Detail

oneWay

public SensitivityFunctionOneWay oneWay(Evidence evidence,
                                        State hypothesis,
                                        ParameterReference parameter)

Calculates how a hypothesis varies based on changes to a single parameter.

Parameters:

evidence - The evidence.

hypothesis - The state whose probability is to be analysed, based on changes to a single parameter.

parameter - The single parameter that can be varied.

Returns:

The sensitivity function.

twoWay

public SensitivityFunctionTwoWay twoWay(Evidence evidence,
                                        State hypothesis,
                                        ParameterReference parameter1,
                                        ParameterReference parameter2)

Calculates how a hypothesis varies based on changes to two parameters.

Parameters:

evidence - The evidence.

hypothesis - The state whose probability is to be analysed, based on changes to a single parameter.

parameter1 - The first parameter that can be varied.

parameter2 - The first parameter that can be varied.

Returns:

The sensitivity function.