Skip to content

vlt.stats.probOfSuper

  vlt.stats.probOfSuper - Probability of Superiority of B over A

  P = vlt.stats.probOfSuper(A, B)

  Calculates the probability that a randomly selected element from vector B
  is greater than a randomly selected element from vector A.

  P = P(B > A) + 0.5 * P(B == A)

  This metric is also known as the Common Language Effect Size (CLES) or
  the Area Under the Receiver Operating Characteristic Curve (AUC).

  It is calculated using the U-statistic from the Mann-Whitney U test.

  Inputs:
    A - a numeric vector of data points for group A
    B - a numeric vector of data points for group B

  Outputs:
    P - The probability of superiority (scalar double between 0 and 1).
        If either A or B is empty (after removing NaNs), NaN is returned.

  Example:
    A = [1, 2, 3];
    B = [2, 3, 4];
    p = vlt.stats.probOfSuper(A, B);

  See also: vlt.stats.ranks2, vlt.stats.mwustat