Kurtosis
Measure of the heaviness of the tails of a distribution relative to the normal.
Also known as: excess kurtosis, g₂
Kurtosis quantifies the heaviness of the tails of a distribution. The commonly reported excess kurtosis is normalised relative to the normal distribution (normal → 0).
Interpretation: g₂ ≈ 0 normal-like (mesokurtic). g₂ > 0 heavy tails, more outliers than expected under normality (leptokurtic). g₂ < 0 light tails, fewer outliers (platykurtic).
See also
Used in
In the Algorithm Lab
Sources
- Joanes, D.N.; Gill, C.A.: Comparing measures of sample skewness and kurtosis, J. R. Statist. Soc. D, 47(1), 1998
- DIN ISO 3534-1: Statistik — Begriffe und Formelzeichen, Teil 1