Package edu.cmu.tetrad.util

Class RankTests.RccaEntry

java.lang.Object
edu.cmu.tetrad.util.RankTests.RccaEntry
Enclosing class:
RankTests
public static final class RankTests.RccaEntry extends Object
Represents an entry in the RCCA (Regularized Canonical Correlation Analysis) data structure. The entry contains singular values in descending order and precomputed logarithmic suffix sums.

This class is private and static, designed to be utilized internally within its enclosing class.

Attributes: - svals: An array of singular values sorted in descending order. - suffixLogs: An array where each element at index `i` represents the sum of logarithms of (1 - squared singular value) from index `i` to the end of the `svals` array.

  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    final double[]
    suffixLogs
    An array where each element at index `i` represents the cumulative sum of the logarithms of (1 - squared singular values) from index `i` to the end of the corresponding singular values array.
    final double[]
    svals
    An array of singular values sorted in descending order.

  • Method Summary

    Methods inherited from class java.lang.Object

    equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

  • Field Details

    • svals

      public final double[] svals
      An array of singular values sorted in descending order. These values represent the singular values of a matrix in the context of Regularized Canonical Correlation Analysis (RCCA). This array is typically used for computations related to matrix decomposition or transformations.

    • suffixLogs

      public final double[] suffixLogs
      An array where each element at index `i` represents the cumulative sum of the logarithms of (1 - squared singular values) from index `i` to the end of the corresponding singular values array. Specifically, `suffixLogs[i]` = Σ log(1 - sj²) for all `j` from `i` to the end. This array is precomputed for efficiency in mathematical or analytical operations related to matrix decomposition or canonical correlation analysis.