Package edu.cmu.tetrad.search

Class IndTestHsic

java.lang.Object
edu.cmu.tetrad.search.IndTestHsic
All Implemented Interfaces:
IndependenceTest
public final class IndTestHsic extends Object implements IndependenceTest
Checks the conditional independence X _||_ Y | S, where S is a set of continuous variable, and X and Y are discrete variable not in S, using the Hilbert-Schmidth Independence Criterion (HSIC), a kernel based nonparametric test for conditional independence.
Author:
Robert Tillman

  • Constructor Details

    • IndTestHsic

      public IndTestHsic(DataSet dataSet, double alpha)
      Constructs a new HSIC Independence test. The given significance level is used.
      Parameters:
      dataSet - A data set containing only continuous columns.
      alpha - The alpha level of the test.

    • IndTestHsic

      public IndTestHsic(Matrix data, List<Node> variables, double alpha)

  • Method Details

    • indTestSubset

      public IndependenceTest indTestSubset(List<Node> vars)
      Creates a new IndTestHsic instance for a subset of the variables.
      Specified by:
      indTestSubset in interface IndependenceTest
      Returns:
      an Independence test for a subset of the variables.

    • checkIndependence

      public IndependenceResult checkIndependence(Node y, Node x, List<Node> z)
      Determines whether variable x is independent of variable y given a list of conditioning variables z.
      Specified by:
      checkIndependence in interface IndependenceTest
      Parameters:
      x - the one variable being compared.
      y - the second variable being compared.
      z - the list of conditioning variables.
      Returns:
      true iff x _||_ y | z.
      See Also:

    • empiricalHSIC

      public double empiricalHSIC(Matrix Ky, Matrix Kx, int m)
      Empirical unconditional Hilbert-Schmidt Dependence Measure for X and Y
      Parameters:
      Ky - centralized Gram matrix for Y
      Kx - centralized Gram matrix for X
      m - sample size

    • empiricalHSICincompleteCholesky

      public double empiricalHSICincompleteCholesky(Matrix Gy, Matrix Gx, int m)
      Empirical unconditional Hilbert-Schmidt Dependence Measure for X and Y using incomplete Cholesky decomposition to approximate Gram matrices
      Parameters:
      Gy - Choleksy approximate Gram matrix for Y
      Gx - Choleksy approximate Gram matrix for X
      m - sample size

    • empiricalHSICincompleteCholesky

      public double empiricalHSICincompleteCholesky(Matrix Gy, Matrix Gx, Matrix Gz, int m)
      Empirical unconditional Hilbert-Schmidt Dependence Measure for X and Y given Z using incomplete Cholesky decomposition to approximate Gram matrices
      Parameters:
      Gy - Choleksy approximate Gram matrix for Y
      Gx - Choleksy approximate Gram matrix for X
      Gz - Choleksy approximate Gram matrix for Z
      m - sample size

    • getThreshold

      public double getThreshold()

    • getPValue

      public double getPValue()
      Returns:
      the probability associated with the most recently computed independence test.

    • setAlpha

      public void setAlpha(double alpha)
      Sets the significance level at which independence judgments should be made.
      Specified by:
      setAlpha in interface IndependenceTest

    • setIncompleteCholesky

      public void setIncompleteCholesky(double precision)
      Sets the precision for the Incomplete Choleksy factorization method for approximating Gram matrices. A value <= 0 indicates that the Incomplete Cholesky method should not be used and instead use the exact matrices.

    • setPerms

      public void setPerms(int perms)
      Set the number of bootstrap samples to use

    • setRegularizer

      public void setRegularizer(double regularizer)
      Sets the regularizer

    • getAlpha

      public double getAlpha()
      Gets the getModel significance level.
      Specified by:
      getAlpha in interface IndependenceTest
      Returns:
      the significance level of the independence test.

    • getPrecision

      public double getPrecision()
      Gets the getModel precision for the Incomplete Cholesky

    • getPerms

      public int getPerms()
      Gets the getModel number of bootstrap samples used

    • getVariables

      public List<Node> getVariables()
      Specified by:
      getVariables in interface IndependenceTest
      Returns:
      the list of variables over which this independence checker is capable of determinine independence relations-- that is, all the variables in the given graph or the given data set.

    • getVariable

      public Node getVariable(String name)
      Specified by:
      getVariable in interface IndependenceTest
      Returns:
      the variable with the given name.

    • getData

      public DataSet getData()
      Specified by:
      getData in interface IndependenceTest
      Returns:
      the data set being analyzed.

    • getScore

      public double getScore()
      Description copied from interface: IndependenceTest
      A score that is higher with more likely models.
      Specified by:
      getScore in interface IndependenceTest

    • toString

      public String toString()
      Specified by:
      toString in interface IndependenceTest
      Overrides:
      toString in class Object
      Returns:
      a string representation of this test.

    • determines

      public boolean determines(List<Node> z, Node x) throws UnsupportedOperationException
      Specified by:
      determines in interface IndependenceTest
      Returns:
      true if y is determined the variable in z.
      Throws:
      UnsupportedOperationException

    • isVerbose

      public boolean isVerbose()
      Specified by:
      isVerbose in interface IndependenceTest

    • setVerbose

      public void setVerbose(boolean verbose)
      Specified by:
      setVerbose in interface IndependenceTest