Package edu.cmu.tetrad.search

Class Lingam

java.lang.Object

edu.cmu.tetrad.search.Lingam

public class Lingam
extends Object

Implements the LiNGAM algorithm in Shimizu, Hoyer, Hyvarinen, and Kerminen, A linear nongaussian acyclic model for causal discovery, JMLR 7 (2006). Largely follows the Matlab code.

We use FGES with knowledge of causal order for the pruning step.

Author:

Joseph Ramsey

Constructor Summary

Constructors

Constructor	Description
Lingam()	Constructs a new LiNGAM algorithm with the given alpha level (used for pruning).

Method Summary

Modifier and Type	Method	Description
Graph	search(DataSet data)
void	setFastIcaA(double fastIcaA)
void	setFastIcaTolerance(double tolerance)
void	setFastMaxIter(int maxIter)
void	setPenaltyDiscount(double penaltyDiscount)

Methods inherited from class java.lang.Object

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

Constructor Details

Lingam

public Lingam()

Constructs a new LiNGAM algorithm with the given alpha level (used for pruning).

Method Details

search

public Graph search(DataSet data)

setPenaltyDiscount

public void setPenaltyDiscount(double penaltyDiscount)

setFastIcaA

public void setFastIcaA(double fastIcaA)

setFastMaxIter

public void setFastMaxIter(int maxIter)

setFastIcaTolerance

public void setFastIcaTolerance(double tolerance)