The KURTOSIS function is part of the IMLMLIB library. The KURTOSIS function returns the sample kurtosis for each column of a matrix. The sample kurtosis measures the heaviness of the tails of a data distribution. The KURTOSIS function returns an estimate for the excess kurtosis, which is 3 less than the standardized fourth central moment.

The KURTOSIS function returns the same sample kurtosis as the UNIVARIATE procedure. For a formula, see the section “Descriptive Statistics” in the chapter “The UNIVARIATE Procedure” in Base SAS Procedures Guide: Statistical Procedures.

The following example computes the kurtosis for each column of a matrix:

x = {1 0,
     2 1,
     4 2,
     8 3,
    16 . };
kurt = kurtosis(x);
print kurt;