🔒 100% private — runs in your browser, nothing is uploaded

Coefficient of Variation Calculator

Divide the standard deviation by the mean to compare spread across different scales.

A standard deviation only makes sense next to its own scale: an SD of 2 is huge for a mean of 5 and trivial for a mean of 5,000. The coefficient of variation fixes that by dividing the standard deviation by the mean and expressing the result as a percentage, so spread becomes unit-free and comparable — a CV of 16.7% means the same relative scatter whether the numbers were grams, seconds or prices. For the sample list above (12, 15, 11, 14, 13, 16, 12, 15) the mean is 13.5 and the sample SD about 1.77, giving a CV of roughly 13.1%.

The headline figure uses the sample standard deviation (dividing by n − 1), which is the right choice when your numbers are a sample drawn from a larger group. The population version (dividing by n) is shown alongside for a complete data set. A coefficient of variation only makes sense for ratio-scale data with a meaningful zero — weights, times, prices — not for temperatures in °C or calendar years.

Quick answers

How do you calculate the coefficient of variation?

CV = standard deviation ÷ mean × 100%. A data set with mean 12 and sample SD 2 has a CV of 16.67%. This page reports the sample CV as the headline and the population CV alongside.

CV only makes sense for ratio-scale data with a real zero, and it is undefined when the mean is zero — the calculator refuses that case rather than printing a meaningless figure.

What does a CV of 20% mean?

The standard deviation is one fifth of the mean: typical values scatter about 20% away from the centre, relative to the size of the measurements themselves.

Whether 20% is “a lot” depends entirely on the field — loose for many biological measures, sloppy for precision manufacturing. Compare like with like.

How to use

  1. Paste your numbers into the box, separated by commas, spaces or new lines — a spreadsheet column pasted straight in works.
  2. Check there are at least two values and that their mean is not zero; the page says plainly when either blocks the calculation.
  3. Read the headline CV (sample version), plus the population version for a complete data set.
  4. Compare it against CVs from other data sets measured in different units — that comparability is the whole point of dividing by the mean.

About this tool

The boundaries matter as much as the formula. CV is only meaningful for ratio-scale data with a true zero (mass, time, money); for interval scales like temperature in °C, where zero is arbitrary, the same data in °F produces a different CV, so the number is an artefact of the unit choice. It also explodes as the mean approaches zero and is undefined at a mean of exactly zero, which is why this page refuses that case instead of printing an astronomical percentage. Finally, CV from very small samples is itself unstable — quote it with the n attached. This calculator reports a descriptive statistic only; it does not certify that any process, product or measurement meets any quality standard.

Frequently asked questions

What is a good coefficient of variation?

There is no universal threshold. In laboratory and manufacturing settings CVs under 5–10% are often treated as tight, while biological and survey data routinely run at 20–50% without anything being wrong. Judge a CV against values from the same kind of measurement, not against a rule of thumb imported from another field.

Should I use the sample or population CV?

Use the sample version when your numbers are a sample drawn from a larger group you did not measure — the usual case. Use the population version only when you hold every value in the group. This page shows the sample CV as the headline and the population CV alongside.

Why does the calculator refuse a mean of zero?

Because CV divides by the mean, and division by zero is undefined. A tiny near-zero mean is almost as bad: the CV becomes enormous and meaningless. Data that straddles zero (changes, differences, profits and losses) is usually better described by the standard deviation alone.

How is CV different from standard deviation?

Standard deviation is in the units of your data; CV is a pure percentage. Two filling machines with SDs of 2 g and 0.5 kg cannot be compared until each SD is divided by its mean — that division is exactly what the coefficient of variation does.

📦 Embed this tool on your site

<iframe src="https://verystep.com/embed/coefficient-of-variation-calculator/" title="Coefficient of Variation Calculator" width="100%" height="520" loading="lazy" style="border:0"></iframe>

Free to use. The embed shows a small "Powered by Verystep" link.

First time embedding? Read the step-by-step guide →

More free tools