Noon Barbari
Sign up
Statistics

Variance

Average squared deviation from the mean. Square root is standard deviation.

Variance is the average of the squared deviations of a series from its mean. It is the building block of standard deviation (its square root) and of more elaborate risk measures like covariance, correlation, and portfolio variance.

Variance is convenient for math (it adds across independent variables) but not for interpretation (it lives in squared-return units). For most trading reporting, standard deviation is reported instead because it shares units with the original returns.

Sample variance divides by N − 1 rather than N (Bessel's correction) to give an unbiased estimate. Most spreadsheet and statistical libraries default to the N − 1 version.

Formula

Var = Σ(x_i − x̄)^2 / (N − 1)

Example

Returns [0.01, -0.02, 0.00, 0.015, -0.005]. Mean = 0. Squared deviations sum to ≈0.000805. Variance = 0.000805 / 4 ≈ 0.000201.

How Noon Barbari uses Variance

Every concept here is implemented in the platform. Open the relevant docs or tool to see it in action.

Volatility calculator

Related terms

Back to glossary