Skewness and kurtosis
In modern data analysis, some high-order moments usually become useful, such as skewness and kurtosis.
- Skewness:
- Measures the asymmetry of the distribution.
- skewness=E[(X−μσ)3]=:γ.
- Gausian has skewness 0, that is, the distribution is symmetric.
- Kurtosis:
- Measure how heavy-tailed the distribution is.
- kurtosis=E[(X−μσ)4]=k
- Gaussian has kurtosis 3.
- Empirical approximations
γ≈1NN∑n=1(Xn−μσ)3
k≈1NN∑n=1(Xn−μσ)4