Współczynnik ekscesu wektora losowego

Excess kurtosis of a univariate random variable is defined as its kurtosis minus 3, i.e. the kurtosis of a normal distribution. Excess kurtosis is a one of a dispersion measures. This parameter provides the information about peakedness and tail weight of a distribution compared to normal distribution. In the paper we propose a generalization of this characteristic for random vectors and analyze its basic properties. Moreover, we introduce the form of excess kurtosis for the selected multivariate distribution.