Coefficient of Variation (CV) Explained

What the coefficient of variation is, how to calculate it, how to read it, and when %CV beats the standard deviation — with worked examples.

6 min read · Reviewed August 2026

What is the coefficient of variation?

The coefficient of variation (CV) — also called the relative standard deviation — is the standard deviation expressed as a percentage of the mean. It measures relative variability: how big the spread is compared with the typical value, rather than in absolute terms.

Because it is a ratio of two quantities in the same units, the CV has no units of its own. That is its superpower: it lets you compare the variability of things measured on completely different scales — dollars against kilograms, exam scores against reaction times.

The coefficient of variation formula

The CV is the standard deviation divided by the mean, times 100%:

CV=\dfrac{s}{\bar{x}}\times 100\%

Use the sample standard deviation and sample mean for sample data, or the population values for a whole population. The result is a single percentage.

Worked example

A coffee machine dispenses cups with a mean of 200 ml and a standard deviation of 10 ml. Its CV is:

CV=\dfrac{10}{200}\times 100\% = 5\%

A second machine fills 1-litre bottles with a mean of 1000 ml and a standard deviation of 20 ml, giving a CV of 2%. The bottle filler has the larger standard deviation (20 vs 10 ml), yet it is actually more consistent relative to its target — its CV is lower. The standard deviation alone would have misled you; the CV makes the fair comparison.

How to interpret the coefficient of variation

A higher CV means more relative variability. As a rough general guide, under 10% is low, 10–30% is moderate, and over 30% is high — but the “right” value is entirely field-dependent:

In a precision lab, an assay might be required to have a CV (there called %RSD) under 2–5%.
In finance, a CV of 30% or more on returns is completely normal.
For biological or survey data, moderate-to-high CVs are typical.

The CV only makes sense for data on a ratio scale with a positive mean. It is undefined when the mean is zero and misleading when values can be negative (like temperatures in °C).

When to use the CV instead of the standard deviation

Comparing variability across data sets with different means or units.
Assessing precision and repeatability in the lab (%RSD).
Measuring risk per unit of return in finance.
Tracking process consistency in quality control across products of different sizes.

When you are describing the spread within a single data set in its own units, the standard deviation is the more natural choice.

Frequently asked questions

What is a good coefficient of variation?

It depends on the field. As a rough rule of thumb, under 10% is low variability, 10–30% is moderate, and above 30% is high. Lab assays often demand a CV under 2–5%, while 30%+ is normal in finance.

What does the coefficient of variation tell you?

It tells you how large the standard deviation is relative to the mean, as a percentage. This lets you compare the variability of data sets that are measured on different scales or in different units.

Is the coefficient of variation the same as the standard deviation?

No. The standard deviation measures spread in the original units. The coefficient of variation is the standard deviation divided by the mean, expressed as a unitless percentage — so it measures relative rather than absolute spread.