Math CentralQuandaries & Queries


Question from Braden:

When determining coefficient of variation (CV) or %CV is it possible to calculate %CV for two variables? For instance can %CV be used to determine the precision of 5 data points on a graph using the X and Y coordinates? or does %CV need to be determined for each variable separately?


As both mean and spread are in some sense vectors, which can only be divided componentwise, separate calculation is needed.

However, for advanced work, it could be useful to do a principal-components analysis, finding new perpendicular axes such that the first axis explains as much of the variation as possible [the "long axis of the blob of data"] and use componentwise coefficients of variation on those instead.

Good Hunting!

About Math Central


Math Central is supported by the University of Regina and The Pacific Institute for the Mathematical Sciences.
Quandaries & Queries page Home page University of Regina PIMS