# increwstdev > Compute an [exponentially weighted standard deviation][moving-average] incrementally.
An [exponentially weighted variance][moving-average] can be defined recursively as
Recursive definition for computing an exponentially weighted variance.
where `μ` is the [exponentially weighted mean][@stdlib/stats/incr/ewmean]. The [exponentially weighted standard deviation][moving-average] is the square root of the [exponentially weighted variance][moving-average].
## Usage ```javascript var increwstdev = require( '@stdlib/stats/incr/ewstdev' ); ``` #### increwstdev( alpha ) Returns an accumulator `function` which incrementally computes an [exponentially weighted standard deviation][moving-average], where `alpha` is a smoothing factor between `0` and `1`. ```javascript var accumulator = increwstdev( 0.5 ); ``` #### accumulator( \[x] ) If provided an input value `x`, the accumulator function returns an updated standard deviation. If not provided an input value `x`, the accumulator function returns the current standard deviation. ```javascript var accumulator = increwstdev( 0.5 ); var s = accumulator(); // returns null s = accumulator( 2.0 ); // returns 0.0 s = accumulator( 1.0 ); // returns 0.5 s = accumulator( 3.0 ); // returns ~0.83 s = accumulator(); // returns ~0.83 ```
## Notes - Input values are **not** type checked. If provided `NaN` or a value which, when used in computations, results in `NaN`, the accumulated value is `NaN` for **all** future invocations. If non-numeric inputs are possible, you are advised to type check and handle accordingly **before** passing the value to the accumulator function.
## Examples ```javascript var randu = require( '@stdlib/random/base/randu' ); var increwstdev = require( '@stdlib/stats/incr/ewstdev' ); var accumulator; var v; var i; // Initialize an accumulator: accumulator = increwstdev( 0.5 ); // For each simulated datum, update the exponentially weighted standard deviation... for ( i = 0; i < 100; i++ ) { v = randu() * 100.0; accumulator( v ); } console.log( accumulator() ); ```