com.bayesserver.analysis

Class DSeparation

java.lang.Object

com.bayesserver.analysis.DSeparation

public final class DSeparation
extends Object

Contains methods to calculate D-Separation.

Method Summary

Modifier and Type	Method and Description
static DSeparationOutput	calculate(Network network, List<Node> sourceNodes, List<Integer> sourceNodeTimes, List<Node> testNodes, List<Integer> testTimes, Evidence evidence, DSeparationOptions options) Calculates whether sets of nodes are D-Separated, given any evidence, and associated times for any temporal nodes.
static DSeparationOutput	calculate(Network network, List<Node> sourceNodes, List<Node> testNodes, Evidence evidence, DSeparationOptions options) Calculates whether sets of nodes are D-Separated, given any evidence.

Methods inherited from class java.lang.Object

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

Method Detail

calculate

public static DSeparationOutput calculate(Network network,
                                          List<Node> sourceNodes,
                                          List<Node> testNodes,
                                          Evidence evidence,
                                          DSeparationOptions options)

Calculates whether sets of nodes are D-Separated, given any evidence.

Parameters:

network - The Bayesian network.

sourceNodes - A set of nodes, which if changed (new evidence set), may or may not affect the test nodes.

testNodes - The nodes we are testing to see if they would be effected by new evidence on any of the source nodes.

evidence - Any existing evidence.

options - Options governing the calculations.

Returns:

An instance which contains the d-separation results for each test node.

calculate

public static DSeparationOutput calculate(Network network,
                                          List<Node> sourceNodes,
                                          List<Integer> sourceNodeTimes,
                                          List<Node> testNodes,
                                          List<Integer> testTimes,
                                          Evidence evidence,
                                          DSeparationOptions options)

Calculates whether sets of nodes are D-Separated, given any evidence, and associated times for any temporal nodes.

Parameters:

network - The Bayesian network.

sourceNodes - A set of nodes, which if changed (new evidence set), may or may not affect the test nodes.

sourceNodeTimes - Any times associated with the test nodes.

testNodes - The nodes we are testing to see if they would be effected by new evidence on any of the source nodes.

testTimes - Any times associated with the test nodes.

evidence - Any existing evidence.

options - Options governing the calculations.

Returns:

An instance which contains the d-separation results for each test node.