Class PhiCorrelationCoefficient

  • All Implemented Interfaces:

    @Reference(authors="A. Agresti",title="Categorical Data Analysis",booktitle="Categorical Data Analysis",bibkey="books/wiley/Agresti90") @Reference(authors="P.-N. Tan, V. Kumar, J. Srivastava",title="Selecting the right objective measure for association analysis",booktitle="Information Systems 29.4",url="",bibkey="DBLP:journals/is/TanKS04")
    public class PhiCorrelationCoefficient
    extends java.lang.Object
    implements InterestingnessMeasure
    Phi Correlation Coefficient interestingness measure.

    \[ \frac{n P(X \cap Y) - P(X) - P(Y)}{\sqrt{P(X)P(Y)P(\neg X)P(\neg Y)}} \]

    This is closely related to the χ² statistic.

    The use for association rule mining was studied in:

    P.-N. Tan, V. Kumar, J. Srivastava
    Selecting the right objective measure for association analysis
    Information Systems 29.4

    Tan et al. attribute this measure to:

    A. Agresti
    Categorical Data Analysis
    Wiley Series in Probability and Statistics

    Abhishek Sharma
    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      double measure​(int t, int sX, int sY, int sXY)
      Computes the value of the measure for a given support values
      • Methods inherited from class java.lang.Object

        clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
    • Constructor Detail

      • PhiCorrelationCoefficient

        public PhiCorrelationCoefficient()
    • Method Detail

      • measure

        public double measure​(int t,
                              int sX,
                              int sY,
                              int sXY)
        Description copied from interface: InterestingnessMeasure
        Computes the value of the measure for a given support values
        Specified by:
        measure in interface InterestingnessMeasure
        t - Total number of transaction
        sX - Support of the antecedent
        sY - Support of the consequent
        sXY - Support of the union of antecedent and consequent
        value of the measure