incrmpcorr

Compute a moving sample Pearson product-moment correlation coefficient incrementally.

The Pearson product-moment correlation coefficient between random variables X and Y is defined as

rho Subscript upper X comma upper Y Baseline equals StartFraction c o v left-parenthesis upper X comma upper Y right-parenthesis Over sigma Subscript upper X Baseline sigma Subscript upper Y Baseline EndFraction

where the numerator is the covariance and the denominator is the product of the respective standard deviations.

For a sample of size W, the sample Pearson product-moment correlation coefficient is defined as

r equals StartFraction sigma-summation Underscript i equals 0 Overscript n minus 1 Endscripts left-parenthesis x Subscript i Baseline minus x overbar right-parenthesis left-parenthesis y Subscript i Baseline minus y overbar right-parenthesis Over StartRoot sigma-summation Underscript i equals 0 Overscript n minus 1 Endscripts left-parenthesis x Subscript i Baseline minus x overbar right-parenthesis squared EndRoot StartRoot sigma-summation Underscript i equals 0 Overscript n minus 1 Endscripts left-parenthesis y Subscript i Baseline minus y overbar right-parenthesis squared EndRoot EndFraction

Usage

var incrmpcorr = require( '@stdlib/stats/incr/mpcorr' );

incrmpcorr( window[, mx, my] )

Returns an accumulator function which incrementally computes a moving sample Pearson product-moment correlation coefficient. The window parameter defines the number of values over which to compute the moving sample Pearson product-moment correlation coefficient.

var accumulator = incrmpcorr( 3 );

If means are already known, provide mx and my arguments.

var accumulator = incrmpcorr( 3, 5.0, -3.14 );

accumulator( [x, y] )

If provided input values x and y, the accumulator function returns an updated sample Pearson product-moment correlation coefficient. If not provided input values x and y, the accumulator function returns the current sample Pearson product-moment correlation coefficient.

var accumulator = incrmpcorr( 3 );

var r = accumulator();
// returns null

// Fill the window...
r = accumulator( 2.0, 1.0 ); // [(2.0, 1.0)]
// returns 0.0

r = accumulator( -5.0, 3.14 ); // [(2.0, 1.0), (-5.0, 3.14)]
// returns ~-1.0

r = accumulator( 3.0, -1.0 ); // [(2.0, 1.0), (-5.0, 3.14), (3.0, -1.0)]
// returns ~-0.925

// Window begins sliding...
r = accumulator( 5.0, -9.5 ); // [(-5.0, 3.14), (3.0, -1.0), (5.0, -9.5)]
// returns ~-0.863

r = accumulator( -5.0, 1.5 ); // [(3.0, -1.0), (5.0, -9.5), (-5.0, 1.5)]
// returns ~-0.803

r = accumulator();
// returns ~-0.803

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 at least W-1 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.
  • As W (x,y) pairs are needed to fill the window buffer, the first W-1 returned values are calculated from smaller sample sizes. Until the window is full, each returned value is calculated from all provided values.

Examples

var randu = require( '@stdlib/random/base/randu' );
var incrmpcorr = require( '@stdlib/stats/incr/mpcorr' );

var accumulator;
var x;
var y;
var i;

// Initialize an accumulator:
accumulator = incrmpcorr( 5 );

// For each simulated datum, update the moving sample correlation coefficient...
for ( i = 0; i < 100; i++ ) {
    x = randu() * 100.0;
    y = randu() * 100.0;
    accumulator( x, y );
}
console.log( accumulator() );