Package smile.stat.hypothesis

Class ChiSqTest

java.lang.Object
smile.stat.hypothesis.ChiSqTest
public class ChiSqTest extends Object
Pearson's chi-square test, also known as the chi-square goodness-of-fit test or chi-square test for independence. Note that the chi-square distribution is only approximately valid for large sample size. If a significant fraction of bins have small numbers of counts (say, < 10), then the statistic is not well approximated by a chi-square probability function.

  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    final double
    chisq
    chi-square statistic
    final double
    CramerV
    Cramér's V is a measure of association between two nominal variables, giving a value between 0 and 1 (inclusive).
    final double
    df
    The degree of freedom of chi-square statistic.
    final String
    method
    The type of test.
    final double
    pvalue
    p-value

  • Constructor Summary

    Constructors
    Constructor
    Description
    ChiSqTest(String method, double chisq, double df, double pvalue)
    Constructor.
    ChiSqTest(String method, double chisq, double df, double pvalue, double CramerV)
    Constructor.

  • Method Summary

    Modifier and Type
    Method
    Description
    static ChiSqTest
    test(int[][] table)
    Independence test on a two-dimensional contingency table.
    static ChiSqTest
    test(int[] bins, double[] prob)
    One-sample Pearson's chi-square test.
    static ChiSqTest
    test(int[] bins, double[] prob, int constraints)
    One-sample Pearson's chi-square test.
    static ChiSqTest
    test(int[] bins1, int[] bins2)
    Two-sample Pearson's chi-square test.
    static ChiSqTest
    test(int[] bins1, int[] bins2, int constraints)
    Two-sample Pearson's chi-square test.
    String
    toString()
     

    Methods inherited from class java.lang.Object

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

  • Field Details

    • method

      public final String method
      The type of test.

    • df

      public final double df
      The degree of freedom of chi-square statistic.

    • chisq

      public final double chisq
      chi-square statistic

    • pvalue

      public final double pvalue
      p-value

    • CramerV

      public final double CramerV
      Cramér's V is a measure of association between two nominal variables, giving a value between 0 and 1 (inclusive). In the case of a 2 × 2 contingency table, Cramér's V is equal to the Phi coefficient.

  • Constructor Details

    • ChiSqTest

      public ChiSqTest(String method, double chisq, double df, double pvalue)
      Constructor.
      Parameters:
      method - the type of test.
      chisq - the chi-square statistic.
      df - the degree of freedom.
      pvalue - the p-value.

    • ChiSqTest

      public ChiSqTest(String method, double chisq, double df, double pvalue, double CramerV)
      Constructor.
      Parameters:
      method - the type of test.
      chisq - the chi-square statistic.
      df - the degree of freedom.
      pvalue - the p-value.
      CramerV - Cramer's V measure.

  • Method Details

    • toString

      public String toString()
      Overrides:
      toString in class Object

    • test

      public static ChiSqTest test(int[] bins, double[] prob)
      One-sample Pearson's chi-square test. Given the array bins containing the observed numbers of events, and an array prob containing the expected probabilities of events, and given one constraint, a small value of p-value indicates a significant difference between the distributions.
      Parameters:
      bins - the observed number of events.
      prob - the expected probabilities of events.
      Returns:
      the test results.

    • test

      public static ChiSqTest test(int[] bins, double[] prob, int constraints)
      One-sample Pearson's chi-square test. Given the array bins containing the observed numbers of events, and an array prob containing the expected probabilities of events, and given the number of constraints (normally one), a small value of p-value indicates a significant difference between the distributions.
      Parameters:
      bins - the observed number of events.
      prob - the expected probabilities of events.
      constraints - the constraints on the degree of freedom.
      Returns:
      the test results.

    • test

      public static ChiSqTest test(int[] bins1, int[] bins2)
      Two-sample Pearson's chi-square test. Given the arrays bins1 and bins2, containing two sets of binned data, and given one constraint, a small value of p-value indicates a significant difference between the distributions.
      Parameters:
      bins1 - the observed number of events in first sample.
      bins2 - the observed number of events in second sample.
      Returns:
      the test results.

    • test

      public static ChiSqTest test(int[] bins1, int[] bins2, int constraints)
      Two-sample Pearson's chi-square test. Given the arrays bins1 and bins2, containing two sets of binned data, and given the number of constraints (normally one), a small value of p-value indicates a significant difference between the distributions.
      Parameters:
      bins1 - the observed number of events in first sample.
      bins2 - the observed number of events in second sample.
      constraints - the constraints on the degree of freedom.
      Returns:
      the test results.

    • test

      public static ChiSqTest test(int[][] table)
      Independence test on a two-dimensional contingency table. The rows of contingency table are the values of one nominal variable, the columns are the values of the other nominal variable. The entries are the number of observed events for each combination of row and column.

      Continuity correction will be applied when computing the test statistic for 2x2 tables: one half is subtracted from all |O-E| differences. The correlation coefficient is calculated as Cramer's V.

      Parameters:
      table - the contingency table.
      Returns:
      the test results.