@stdlib/stats-incr-ewstdev NPM

increwstdev

Compute an exponentially weighted standard deviation incrementally.

An exponentially weighted variance can be defined recursively as

where μ is the exponentially weighted mean. The exponentially weighted standard deviation is the square root of the exponentially weighted variance.

Installation

npm install @stdlib/stats-incr-ewstdev

Usage

var increwstdev = require( '@stdlib/stats-incr-ewstdev' );

increwstdev( alpha )

Returns an accumulator function which incrementally computes an exponentially weighted standard deviation, where alpha is a smoothing factor between 0 and 1.

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.

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

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() );

Notice

This package is part of stdlib, a standard library for JavaScript and Node.js, with an emphasis on numerical and scientific computing. The library provides a collection of robust, high performance libraries for mathematics, statistics, streams, utilities, and more.

For more information on the project, filing bug reports and feature requests, and guidance on how to develop stdlib, see the main project repository.