Skip to content

Mathematics · Ch 11 — Probability Distributions

Variance

11.5.2

Variance

Definition 11.9 (Variance). The variance of XX, written V(X)V(X), Var(X)\text{Var}(X), or σ2\sigma^2, is

V(X)=E((X−E(X))2).V(X)=E\big((X-E(X))^2\big).

It measures how the data spread out from the mean — the average of the squared deviations from μ\mu. (Variability, spread and dispersion are synonyms.) The standard deviation is σ=V(X)\sigma=\sqrt{V(X)}; both V(X)V(X) and σ\sigma are always ≥0\ge0.

Alternative computing formula. Expanding the square and using linearity of expectation (proved formally in §11.5.3) gives the far more convenient

V(X)=E(X2)−(E(X))2V(X)=E(X^2)-\big(E(X)\big)^2

— compute the mean and the second moment E(X2)E(X^2) separately, then subtract the square of the mean. This is the formula used throughout the exercises. …