# incrcovariance
> Compute an [unbiased sample covariance][covariance] incrementally.
For unknown population means, the [unbiased sample covariance][covariance] is defined as
For known population means, the [unbiased sample covariance][covariance] is defined as
## Usage
```javascript
var incrcovariance = require( '@stdlib/stats/incr/covariance' );
```
#### incrcovariance( \[mx, my] )
Returns an accumulator `function` which incrementally computes an [unbiased sample covariance][covariance].
```javascript
var accumulator = incrcovariance();
```
If the means are already known, provide `mx` and `my` arguments.
```javascript
var accumulator = incrcovariance( 3.0, -5.5 );
```
#### accumulator( \[x, y] )
If provided input values `x` and `y`, the accumulator function returns an updated [unbiased sample covariance][covariance]. If not provided input values `x` and `y`, the accumulator function returns the current [unbiased sample covariance][covariance].
```javascript
var accumulator = incrcovariance();
var v = accumulator( 2.0, 1.0 );
// returns 0.0
v = accumulator( 1.0, -5.0 );
// returns 3.0
v = accumulator( 3.0, 3.14 );
// returns 4.07
v = accumulator();
// returns 4.07
```
## 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 incrcovariance = require( '@stdlib/stats/incr/covariance' );
var accumulator;
var x;
var y;
var i;
// Initialize an accumulator:
accumulator = incrcovariance();
// For each simulated datum, update the unbiased sample covariance...
for ( i = 0; i < 100; i++ ) {
x = randu() * 100.0;
y = randu() * 100.0;
accumulator( x, y );
}
console.log( accumulator() );
```
[covariance]: https://en.wikipedia.org/wiki/Covariance
