Hi All,
I’m trying to calculate the correlation coefficient between two arrays. I basically want to replicate the Excel “CORREL” function, where I input the two arrays and the function outputs the correlation value.
Does anyone have working code to do this and be willing to share it?
The best I have found so far is the code below I found on another forum, but it’s giving me incorrect answers. Well answers that are different to what I get in Excel anyway!
Any help much appreciated!
Thanks!
#define RET_OK 0
#define RET_ERROR EMPTY
#define VAL_ERROR EMPTY_VALUE
int PearsonCorr_r( double const &vectorX[], // |-> INPUT X[] = { 1, 3, 5, 5, 6 }
double const &vectorY[], // |-> INPUT Y[] = { 5, 6, 10, 12, 13 }
double &pearson_r // <=| returns RESULT = 0.968
)
{
double sumX = 0,
meanX = 0,
meanY = 0,
sumY = 0,
sumXY = 0,
sumX2 = 0,
sumY2 = 0;
// deviation_score_x[], // may be re-used for _x^2
// deviation_score_y[], // may be re-used for _y^2
// deviation_score_xy[];
/* =====================================================================
DEVIATION SCORES >>> http://onlinestatbook.com/2/describing_bivariate_data/calculation.html
X[] Y[] x y xy x^2 y^2
1 4 -3 -5 15 9 25
3 6 -1 -3 3 1 9
5 10 1 1 1 1 1
5 12 1 3 3 1 9
6 13 2 4 8 4 16
_______________________________________
SUM 20 45 0 0 30 16 60
MEAN 4 9 0 0 6
r = SUM(xy) / SQRT( SUM( x^2 ) * SUM( y^2 ) )
r = 30 / SQRT( 960 )
r = 0.968
=====================================================================
*/
int vector_maxLEN = MathMin( ArrayRange( vectorX, 0 ),
ArrayRange( vectorY, 0 )
);
if ( vector_maxLEN == 0 ){
pearson_r = VAL_ERROR; // STOR VAL ERROR IN RESULT
return( RET_ERROR ); // FLAG RET_ERROR in JIT/RET
}
for ( int jj = 0; jj < vector_maxLEN; jj++ ){
sumX += vectorX[jj];
sumY += vectorY[jj];
}
meanX = sumX / vector_maxLEN; // DIV!0 FUSED
meanY = sumY / vector_maxLEN; // DIV!0 FUSED
for ( int jj = 0; jj < vector_maxLEN; jj++ ){
// deviation_score_x[ jj] = meanX - vectorX[jj]; //
// deviation_score_y[ jj] = meanY - vectorY[jj];
// deviation_score_xy[jj] = deviation_score_x[jj]
// * deviation_score_y[jj];
// sumXY += deviation_score_x[jj]
// * deviation_score_y[jj];
sumXY += ( meanX - vectorX[jj] ) // PSPACE MOTIVATED MINIMALISTIC WITH CACHE-BENEFITS IN PROCESSING
* ( meanY - vectorY[jj] );
// deviation_score_x[jj] *= deviation_score_x[jj]; // PSPACE MOTIVATED RE-USE, ROW-WISE DESTRUCTIVE, BUT VALUE WAS NEVER USED AGAIN
// sumX2 += deviation_score_x[jj]
// * deviation_score_x[jj];
sumX2 += ( meanX - vectorX[jj] ) // PSPACE MOTIVATED MINIMALISTIC WITH CACHE-BENEFITS IN PROCESSING
* ( meanX - vectorX[jj] );
// deviation_score_y[jj] *= deviation_score_y[jj]; // PSPACE MOTIVATED RE-USE, ROW-WISE DESTRUCTIVE, BUT VALUE WAS NEVER USED AGAIN
// sumY2 += deviation_score_y[jj]
// * deviation_score_y[jj];
sumY2 += ( meanY - vectorY[jj] ) // PSPACE MOTIVATED MINIMALISTIC WITH CACHE-BENEFITS IN PROCESSING
* ( meanY - vectorY[jj] );
}
pearson_r = sumXY
/ MathSqrt( sumX2
* sumY2
); // STOR RET VALUE IN RESULT
return( RET_OK ); // FLAG RET_OK in JIT/RET
}