Package edu.cmu.tetrad.search

Class Fofc

java.lang.Object

edu.cmu.tetrad.search.Fofc

public class Fofc
extends Object

Implements the Find One Factor Clusters (FOFC) algorithm by Erich Kummerfeld, which uses reasoning about vanishing tetrads of algorithms to infer clusters of the measured variables in a dataset that each be explained by a single latent variable. A reference is the following

Kummerfeld, E., & Ramsey, J. (2016, August). Causal clustering for 1-factor measurement models. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1655-1664).

The algorithm employs tests of vanishing tetrads (list of 4 variables that follow a certain pattern in the exchangeability of latent paths with respect to the data). The notion of vanishing tetrads is old one but is explained in this book:

Spirtes, P., Glymour, C. N., Scheines, R., & Heckerman, D. (2000). Causation, prediction, and search. MIT press.

Author:

peterspirtes, erichkummerfeld, josephramsey

See Also:

• Ftfc
• Bpc

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static enum	Fofc.Algorithm	Gives the options to be used in FOFC to sort through the various possibilities for forming clusters to find the best options.

Constructor Summary

Constructors

Constructor	Description
Fofc(DataSet dataSet, BpcTestType testType, Fofc.Algorithm algorithm, double alpha)	Conctructor.
Fofc(ICovarianceMatrix cov, BpcTestType testType, Fofc.Algorithm algorithm, double alpha)	Constructor.

Method Summary

Modifier and Type	Method	Description
List<List<Node>>	getClusters()	The clusters that are output by the algorithm from the last call to search().
Graph	search()	Runs the search and returns a graph of clusters with the ir respective latent parents.
void	setCheckType(ClusterSignificance.CheckType checkType)	Sets which type of cluster check should be performed.
void	setSignificanceChecked(boolean significanceChecked)	Sets whether the significance of the cluster should be checked for each cluster.
void	setVerbose(boolean verbose)

Methods inherited from class java.lang.Object

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

Constructor Details

Fofc

public Fofc(ICovarianceMatrix cov,
 BpcTestType testType,
 Fofc.Algorithm algorithm,
 double alpha)

Constructor.

Parameters:

cov - The covariance matrix searched over.

testType - The type of test used.

algorithm - The type of FOFC algorithm used.

alpha - The alpha significance cutoff.

See Also:

• BpcTestType
• Fofc.Algorithm

Fofc

public Fofc(DataSet dataSet,
 BpcTestType testType,
 Fofc.Algorithm algorithm,
 double alpha)

Conctructor.

Parameters:

dataSet - The continuous dataset searched over.

testType - The type of test used.

algorithm - The type of FOFC algorithm used.

alpha - The alpha significance cutoff.

See Also:

• BpcTestType
• Fofc.Algorithm

Method Details

search

public Graph search()

Runs the search and returns a graph of clusters with the ir respective latent parents.

Returns:

This graph.

setSignificanceChecked

public void setSignificanceChecked(boolean significanceChecked)

Sets whether the significance of the cluster should be checked for each cluster.

Parameters:

significanceChecked - True, if so.

setCheckType

public void setCheckType(ClusterSignificance.CheckType checkType)

Sets which type of cluster check should be performed.

Parameters:

checkType - The type to be performed.

See Also:

• ClusterSignificance.CheckType

getClusters

public List<List<Node>> getClusters()

The clusters that are output by the algorithm from the last call to search().

setVerbose

public void setVerbose(boolean verbose)