In statistics, the Pearson correlation coefficient, also referred to as Pearson’s r, the Pearson product-moment correlation coefficient (PPMCC), is a measure of linear correlation between two sets of data. It is the covariance of two variables, divided by the product of their standard deviations; thus it is essentially a normalised measurement of the covariance, such that the result always has a value between −1 and 1.  https://en.wikipedia.org/wiki/Pearson_correlation_coefficient

It’s not to be confused with R2 – Coefficient of determination – https://www.prorealcode.com/prorealtime-indicators/r-squared-correlation-coefficient-r2/

//ρ (rho) = cov(x, y) / sd(x) * sd(y), where cov is covariance, sd(x) is the standard deviation of x

// cov(x,y) = ((x - E(x) * (y - E(y) ), where E(x) is the Expected Value of x

// E(x) = average(x),  the expected value is the weighted sum of the xi values, with the probabilities pi as the weights. When values of x are equiprobable, then the weighted average turns into the simple average.

// sd(x) = square root (variance(x;xn))

// variance(x;xn) = (x-(average(x1;xn))^2 / n

Period = 5

IF barindex>Period THEN

X         = close
VarianceX = average[Period](SQUARE((X - average[Period](X))))
sdX       = SQRT(VarianceX)

Y         = RSI[8](close)
VarianceY = average[Period](SQUARE((Y - average[Period](Y))))
sdY       = SQRT(VarianceY)

covXY     = average[Period]((X-average[Period](X)) * (Y-average[Period](Y)))

R        = covXY / (sdX * sdY)

ENDIF

RETURN R

While the above code considers the correlation between two variables at the most current bar and based on other historical values, I wonder if it’s not more appropriate to compare current [P] X to previous [P-1] Y , so that one can at least predict the direction of X based on previous Y (previous closed bar).

Now, the most difficult is to find the best suited Y (RSI? Stoch? Volume? or a combination of a few indicators? calculated on the same period than X or on a different period? etc.)

Please share your thoughts or any improvement you may think of.