PartialCorrelationTest
javanpst.tests.multiple.partialCorrelationTest

Class PartialCorrelationTest



  • public class PartialCorrelationTestextends StatisticalTest
    A test based on partial correlation. This procedure can be applied to test independence of 2 variables, X and Y, when the effect of a third variable, Z, is removed. The test statistic is computed by finding the number of concordant (C) and discordant (Q) pairs existing in pairs X-Y, X-Z and Y-Z. Kendall's tau coefficient is also provided. Note: This test is not recommended for more than 20 samples
    • Constructor Detail

      • PartialCorrelationTest

        public PartialCorrelationTest()
        Default builder
      • PartialCorrelationTest

        public PartialCorrelationTest(DataTable newData)
        Builder. Load data to test.
        Parameters:
        newData - data to test.
    • Method Detail

      • setData

        public void setData(DataTable newData)
        Sets data to test
        Parameters:
        newData - data to test.
      • getTau

        public double getTau()
        Get tau statistic
        Returns:
        tau statistic
      • getPValue

        public double getPValue()
        Get p-value
        Returns:
        p-value computed

SCaVis 2.2 © jWork.ORG

Warning: The reason why you see this message is because an access to the API documentation of third-party Java classes is denied for non-members. Guests can only view jhplot API. To enable links to the description of all Java classes, please request the full SCaVis membership.