VAR

Summary

Rolling population variance of a real series over a given period. Measures dispersion of values around their mean. Higher values indicate greater dispersion; 0 means constant input.

Formula

$\mathrm{VAR} = \frac{1}{n}\sum x_i^2 - \left(\frac{1}{n}\sum x_i\right)^2$, over the last $n$ = optInTimePeriod values (population, divides by $n$).

Notes

• Computes population variance (divides by the period), not the sample variance (n-1) used by some definitions.
• The deviation-count parameter is accepted but has no effect on the result.

Inputs

• inReal — Source series

Outputs

• outReal — Rolling population variance

Parameters

Parameter	Type	Default	Accepted values	Description
optInTimePeriod	integer	5	1–100000	Window length for the variance
optInNbDev	real	1	any real	Deviation count accepted by the API but never used in the computation

Properties

Numerical Stability: Start-Independent

Display Flags
☐ Overlap Input
✅ Independent Y-Axis i
☐ Candlestick

Implementation

TA-Lib Definition: var.c · var.yaml

Native	File
C	ta_VAR.c
Rust	var.rs
Java	Core_VAR.java

TA-Lib is also available for Python, R and more using a wrapper.

Aliases

Variance

See Also

STDDEV