# itercugmean > Create an [iterator][mdn-iterator-protocol] which iteratively computes a cumulative [geometric mean][geometric-mean].
The [geometric mean][geometric-mean] is defined as the nth root of a product of _n_ numbers.
Equation for the geometric mean.
## Usage ```javascript var itercugmean = require( '@stdlib/stats/iter/cugmean' ); ``` #### itercugmean( iterator ) Returns an [iterator][mdn-iterator-protocol] which iteratively computes a cumulative [geometric mean][geometric-mean]. ```javascript var array2iterator = require( '@stdlib/array/to-iterator' ); var arr = array2iterator( [ 2.0, 1.0, 3.0, 7.0, 5.0 ] ); var it = itercugmean( arr ); var v = it.next().value; // returns 2.0 v = it.next().value; // returns ~1.41 v = it.next().value; // returns ~1.82 v = it.next().value; // returns ~2.55 v = it.next().value; // returns ~2.91 ```
## Notes - If an iterated value is non-numeric (including `NaN`) or negative, the function returns `NaN` for **all** future iterations. If non-numeric and/or negative iterated values are possible, you are advised to provide an [`iterator`][mdn-iterator-protocol] which type checks and handles such values accordingly.
## Examples ```javascript var runif = require( '@stdlib/random/iter/uniform' ); var itercugmean = require( '@stdlib/stats/iter/cugmean' ); // Create an iterator for generating uniformly distributed pseudorandom numbers: var rand = runif( 0.0, 10.0, { 'seed': 1234, 'iter': 100 }); // Create an iterator for iteratively computing a cumulative geometric mean: var it = itercugmean( rand ); // Perform manual iteration... var v; while ( true ) { v = it.next(); if ( typeof v.value === 'number' ) { console.log( 'gmean: %d', v.value ); } if ( v.done ) { break; } } ```