Introduction
Often, it is important to determine how two variables are associated. Parametric statistics provides two measures of association, the covariance and the correlation coefficient. Covariance is the sum of the cross-products of the deviations of each variable from its respective mean. It suffers from the fact that its magnitude has no particular meaning because it can be changed by changing the units of measurement of the two variables. Dividing the covariance by the standard deviations of the two variables yields the correlation coefficient, which eliminates the unit of measurement problem because it does not have any units.
The term correlation coefficient is typically used to refer to the parametric ...
Get A Primer on Nonparametric Analysis, Volume II now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
