Requires: MathScript RT Module
r = corrcoeff(x)
r = corrcoeff(x, y)
[r, p, rlo, rup] = corrcoeff(x, 'alpha', a, 'rows', s)
[r, p, rlo, rup] = corrcoeff(x, y, 'alpha', a, 'rows', s)
Computes the correlation coefficients.
|x||Specifies observations for each variable. If you specify r = corrcoeff(x), x can be real or complex. If you specify [r, p, rlo, rup] = corrcoeff(x, 'alpha', a, 'rows', s), x must be real. x is a vector or matrix. If x is a vector, each element in x is an observation. If x is a matrix, each row in x is an observation, and each element in the row is data for that observation.|
|y||When x is a vector, y specifies the data values for each observation in x. When x is a matrix, you cannot specify y. y is an array of the same length as x.|
|'alpha'||Tells LabVIEW that the next listed input is a.|
|a||Specifies the confidence level 1-a. a is a real number in the interval [0, 1]. The default is 0.05.|
|'rows'||Tells LabVIEW that the next listed input is s.|
|s||Specifies how to handle values of NaN in x. s is a string that accepts the following values.
|r||Returns the correlation coefficients.|
|p||Returns the p-values for the null hypothesis. p is a matrix.|
|rlo||Returns the lower bound for the confidence interval of each coefficient. rlo is a matrix.|
|rup||Returns the upper bound for the confidence interval of each coefficient. rup is a matrix.|
If you specify both inputs x and y, LabVIEW computes the correlation coefficients according to the following equation: r = corrcoeff([x(:), y(:)]).
The following table lists the support characteristics of this function.
|Supported in the LabVIEW Run-Time Engine||Yes|
|Supported on RT targets||Yes|
|Suitable for bounded execution times on RT||Not characterized|
R = corrcoeff(rand(5, 6))
R = corrcoeff(rand(5, 1), rand(5, 1))
[R, P, RLO, RUP] = corrcoeff(rand(5, 6))