FTB-C000480 / Statistical method

Rolling Population Variance

Rolling Population Variance is the mean squared deviation from the arithmetic mean inside each active window.

Also known aspopulation rolling variance

Definitions

In plain terms

It treats the n values in the selected window as the full set being described and therefore divides by n.

Technical

The window, center, denominator, current-row inclusion, missing-value policy, numerical algorithm, and first-ready row must be declared.

Scope

It differs from sample variance, which uses an n-minus-one denominator for an inferential estimate.

Formula

Population variance = sum((x_i - mean)^2) / n
LaTeX: \sigma^2=\frac{1}{n}\sum_{i=1}^{n}(x_i-\bar{x})^2
SymbolMeaningUnit
x_iwindow value iinput units
bar{x}window arithmetic meaninput units
nwindow countobservations

Output unit: squared input units

Examples

  • A reviewer traces Rolling Population Variance from aligned inputs through its first-ready row and edge cases before accepting a displayed value.

Common misconceptions

  • It differs from sample variance, which uses an n-minus-one denominator for an inferential estimate.

Concept relationships

Where this concept is used

Evidence and governance

  1. TA-Lib Bollinger Bands TA-Lib · first party technical publication

    Supports: preferred label, short definition, technical definition, formula

    Limits: TA-Lib permits moving-average variants beyond the local close-SMA and population-deviation contract.

  2. Measures of Scale NIST/SEMATECH · official standard

    Supports: preferred label, short definition, technical definition, formula

    Limits: The statistical reference does not define Bollinger Bands or validate financial forecasts from price dispersion.

Reviewed by
fintech-builder-batch-009
Last reviewed
2026-07-30
Next review
2027-07-30
Record status
published