Package edu.cmu.tetrad.search

Class ConditionalGaussianOtherLikelihood

java.lang.Object

edu.cmu.tetrad.search.ConditionalGaussianOtherLikelihood

public class ConditionalGaussianOtherLikelihood
extends Object

Implements a conditional Gaussian likelihood. Please note that this this likelihood will be maximal only if the the continuous mixedVariables are jointly Gaussian conditional on the discrete mixedVariables; in all other cases, it will be less than maximal. For an algorithm like FGS this is fine.

Author:

Joseph Ramsey

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	ConditionalGaussianOtherLikelihood.Ret	A return value for a likelihood--returns a likelihood value and the degrees of freedom for it.

Constructor Summary

Constructors

Constructor	Description
ConditionalGaussianOtherLikelihood(DataSet dataSet)	Constructs the score using a covariance matrix.

Method Summary

Modifier and Type	Method	Description
ConditionalGaussianOtherLikelihood.Ret	getLikelihood(int i, int[] parents)	Returns the likelihood of variable i conditional on the given parents, assuming the continuous mixedVariables index by i or by the parents are jointly Gaussian conditional on the discrete comparison.
double	getPenaltyDiscount()
void	setNumCategoriesToDiscretize(int numCategoriesToDiscretize)
void	setPenaltyDiscount(double penaltyDiscount)

Methods inherited from class java.lang.Object

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

Constructor Details

ConditionalGaussianOtherLikelihood

public ConditionalGaussianOtherLikelihood(DataSet dataSet)

Constructs the score using a covariance matrix.

Method Details

getLikelihood

public ConditionalGaussianOtherLikelihood.Ret getLikelihood(int i,
 int[] parents)

Returns the likelihood of variable i conditional on the given parents, assuming the continuous mixedVariables index by i or by the parents are jointly Gaussian conditional on the discrete comparison.

Parameters:

i - The index of the conditioned variable.

parents - The indices of the conditioning mixedVariables.

Returns:

The likelihood.

getPenaltyDiscount

public double getPenaltyDiscount()

setPenaltyDiscount

public void setPenaltyDiscount(double penaltyDiscount)

setNumCategoriesToDiscretize

public void setNumCategoriesToDiscretize(int numCategoriesToDiscretize)