Package com.bayesserver.statistics

Class MutualInformation

java.lang.Object

com.bayesserver.statistics.MutualInformation

public final class MutualInformation
extends Object

Calculates mutual information or conditional mutual information, which measures the dependence between two variables.

Method Summary

Modifier and Type	Method	Description
static double	calculate(Distribution joint, VariableContext x, VariableContext y, LogarithmBase logarithmBase)	Measures the dependence between two variables.
static double	calculate(Distribution joint, VariableContext x, VariableContext y, List<VariableContext> conditionOn, LogarithmBase logarithmBase)	Calculates mutual information or conditional mutual information, which measures the dependence between two variables.
static double	calculate(Distribution joint, List<VariableContext> x, List<VariableContext> y, List<VariableContext> conditionOn, LogarithmBase logarithmBase)	Calculates mutual information or conditional mutual information, which measures the dependence between two variables.

Methods inherited from class java.lang.Object

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

Method Detail

calculate

public static double calculate(Distribution joint,
                               VariableContext x,
                               VariableContext y,
                               LogarithmBase logarithmBase)

Measures the dependence between two variables.

Parameters:

joint - The joint distribution over two (head) variables.

x - X in the expression I(X,Y).

y - Y in the expression I(X,Y).

logarithmBase - The logarithm base to use for the calculations.

Returns:

The mutual information value.

calculate

public static double calculate(Distribution joint,
                               VariableContext x,
                               VariableContext y,
                               List<VariableContext> conditionOn,
                               LogarithmBase logarithmBase)

Calculates mutual information or conditional mutual information, which measures the dependence between two variables.

Parameters:

joint - The joint distribution over two or more variables.

x - X in the expression I(X,Y) or I(X,Y|Z).

y - Y in the expression I(X,Y) or I(X,Y|Z).

conditionOn - Any conditional variables. I.e. Z in the expression I(X,Y|Z) when calculating conditional mutual information.

logarithmBase - The logarithm base to use for the calculations.

Returns:

The mutual information value.

calculate

public static double calculate(Distribution joint,
                               List<VariableContext> x,
                               List<VariableContext> y,
                               List<VariableContext> conditionOn,
                               LogarithmBase logarithmBase)

Calculates mutual information or conditional mutual information, which measures the dependence between two variables.

Parameters:

joint - The joint distribution over two or more variables.

x - X in the expression I(X,Y) or I(X,Y|Z).

y - Y in the expression I(X,Y) or I(X,Y|Z).

conditionOn - Any conditional variables. I.e. Z in the expression I(X,Y|Z) when calculating conditional mutual information.

logarithmBase - The logarithm base to use for the calculations.

Returns:

The mutual information value.