MATLAB: Is it possible to compute Spearman’s rank correlation in MATLAB

Question

I would like to compute Spearman's rank correlation using MATLAB or the Statistics Toolbox.

Answer 1

In the Statistics Toolbox 5.0 (R14), the CORR function can compute Spearman's rank correlation. The syntax is as follows:

rho = corr(X, Y, 'type', 'Spearman');

where 'type' is a type of correlation, specified as the comma-separated. The acceptable values include 'Pearson', 'Kendall' and 'Spearman'. Please refer to the following link for more information:

https://www.mathworks.com/help/stats/corr.html

For previous product releases, please read below for any possible workarounds:

You can easily code the Spearman rank correlation, however, using the existing functions from the Statistics Toolbox.

Here are some functions that will assist you:

TIEDRANK Compute the ranks of a sample, adjusting for ties

CORRCOEF Computes the Correlation coefficients