Module imagingbook.common
Package imagingbook.common.math

Class Statistics

java.lang.Object
imagingbook.common.math.Statistics
public abstract class Statistics extends Object
This class defines static methods for statistical calculations.

  • Method Details

    • meanVector

      public static double[] meanVector(double[][] samples)
      Calculates the mean vector for a sequence of sample vectors.
      Parameters:
      samples - a 2D array of m-dimensional vectors (double[n][m]})
      Returns:
      the mean vector for the sample data (of length m)

    • covarianceMatrix

      public static double[][] covarianceMatrix(double[][] samples)
      Calculates the covariance matrix for a sequence of sample vectors. Takes a sequence of n data samples, each of dimension m. The data element samples[i][j] refers to the j-th component of sample i. No statistical bias correction is applied. Uses Covariance from Apache Commons Math.
      Parameters:
      samples - a 2D array of m-dimensional vectors (double[n][m]})
      Returns:
      the covariance matrix for the sample data (of dimension m x m)
      See Also:

    • covarianceMatrix

      public static double[][] covarianceMatrix(double[][] samples, boolean biasCorrect)
      Calculates the covariance matrix for a sequence of sample vectors. Takes a sequence of n data samples, each of dimension m. The data element samples[i][j] refers to the j-th component of sample i. Statistical bias correction is optionally applied. Uses Covariance from Apache Commons Math.
      Parameters:
      samples - a 2D array of m-dimensional vectors (double[n][m]).
      biasCorrect - if true, statistical bias correction is applied.
      Returns:
      the covariance matrix for the sample data (of dimension m x m).
      See Also:

    • conditionCovarianceMatrix

      public static double[][] conditionCovarianceMatrix(double[][] cov, double minDiagVal)
      Conditions the supplied covariance matrix by enforcing positive eigenvalues.
      Parameters:
      cov - original covariance matrix
      minDiagVal - the minimum positive value of diagonal elements
      Returns:
      conditioned covariance matrix

    • conditionCovarianceMatrix

      public static RealMatrix conditionCovarianceMatrix(RealMatrix cov, double minDiagVal)
      Conditions the supplied covariance matrix by enforcing positive eigenvalues.
      Parameters:
      cov - original covariance matrix
      minDiagVal - the minimum positive value of diagonal elements
      Returns:
      conditioned covariance matrix