Just a short one again. This time I will explain the **coefficient of variation**. And once again give you a full code example of how you can implement it in c#.

The coefficient of variation (CV) is a normalized measure of dispersion. It is a measure of consistency indicating the uniformity in the values of the signal from the mean of the signal. A smaller coefficient of variation indicates a more consistent signal. The values are more uniformly dispersed.

Coefficient of variation is useful when comparing data with different units. For example in the SoapSynergy project I am working on I often have to make comparisons between displacement and angles. Since those signals have different units ((centi)meters versus degrees) it is useful to have a dimensionless number to compare with.

The downside of the coefficient of variation is that it is quite sensitive to changes in the mean. So if your signal moves around the 0 (as a sine wave does) making your mean ~=0, the coefficient of variation can quickly jump to near infinite numbers rendering it useless. For this reason I chose to calculate the coefficient of variation using the absolute values of my signals.

Continue reading