AS/A2 Stats 1 Stats 2

S3 Topic 5: Regression and correlation
Spearman’s rank correlation coefficient
Spearman rank correlation can be applied to compare two independent random variables, each at several levels (which may be discrete or continuous). Unlike the product moment correlation coefficient, Spearman's rank correlation works on ranked (relative) data, rather than directly on the data itself. A value of the coefficient near one indicates good agreement; a value near zero, poor agreement. Of course, as a distribution-free method, the Spearman rank correlation does not make any assumptions about the distribution of the underlying data. Spearman's method works by assigning a rank to each observation in each group separately . Then calculate the coefficient, rs, according to the formula
where d is the difference between the ranks and n is the number of observations. In the display that will appear, enter data in pairs separated by commas, or select Example data and then press Compute. You can also cut and paste data from other sources.

an applet from Stats 101