Coefficient of Variation Calculator (CV)
Calculate the coefficient of variation to compare relative variability across data sets — get the mean, standard deviation, and CV% instantly.
Enter a comma-separated list of numbers and click Calculate to see the mean, sample standard deviation, and coefficient of variation.
Coefficient of Variation Calculator (CV)
Calculate the coefficient of variation to compare relative variability across data sets — get the mean, standard deviation, and CV% instantly.
Enter numbers separated by commas or spaces (at least 2 values required).
About the Coefficient of Variation Calculator
The coefficient of variation (CV), also called the relative standard deviation (RSD), is a standardized measure of statistical dispersion. It is defined as the ratio of the sample standard deviation to the absolute value of the mean, expressed as a percentage: CV = (s / |mean|) × 100%. Because it is dimensionless, the CV lets you compare variability across data sets that have different units or very different magnitudes — something that the raw standard deviation cannot do.
Understanding why this matters becomes clear with a simple example. Suppose Stock A has a mean daily price of $100 and a standard deviation of $5, while Stock B has a mean daily price of $500 and a standard deviation of $20. Stock B has a larger absolute standard deviation, but its CV is only 4% compared to Stock A's 5%. An investor measuring pure relative risk would correctly conclude that Stock A is proportionally more volatile, even though its dollar swings are smaller.
The CV is especially valuable in fields that routinely compare measurements with different scales. In manufacturing quality control, engineers use it to assess whether a production process is consistent regardless of the nominal size of the part being made. A machining process turning out bolts with a diameter of 5 mm and a CV of 0.5% is just as consistent, proportionally, as one producing shafts with a diameter of 50 mm and a CV of 0.5% — even though the second process has ten times the absolute spread. In the life sciences, researchers compare CV values to gauge assay precision: a CV below 5% is typically considered excellent for a laboratory assay, while values above 15–20% may signal measurement noise or poor reproducibility.
This calculator uses the sample standard deviation formula — dividing by n − 1 rather than n — which gives an unbiased estimate of the population standard deviation from a sample. This is the conventional choice whenever you are treating your data as a sample drawn from a larger population, as is the case in most scientific, engineering, and business contexts. If you are computing the CV of a complete population (every member counted), substitute the population standard deviation by replacing n − 1 with n in the denominator.
A few caveats apply when interpreting CV values. The CV is only meaningful when the data are measured on a ratio scale with a true, meaningful zero — such as weight, length, concentration, or price. It is not appropriate for interval data whose zero is arbitrary, such as Celsius temperature or calendar year, because the mean can take any sign and the ratio loses its interpretive value. Additionally, the CV is sensitive to the mean: when the mean is close to zero, even a small standard deviation produces an enormous CV, which can be misleading. Always inspect the raw mean alongside the CV before drawing conclusions.
For the examples in this calculator, the stock price scenario illustrates how two assets with similar absolute volatility can appear quite different once you account for their price levels. The manufacturing precision scenario shows how CV helps set process quality benchmarks independent of part size. The athlete performance scenario demonstrates how coaches can use CV to identify which players are the most consistent contributors across a season, helping inform lineup decisions and contract negotiations.
Coefficient of Variation Examples
Three practical scenarios showing how CV compares relative variability across different domains.
| Data Set | CV | Interpretation |
|---|---|---|
| 100, 102, 105, 98, 103 (Stock A prices) | CV ≈ 2.66% | Low relative volatility — typical of a stable blue-chip stock. Mean = 101.6, SD ≈ 2.70. |
| 10.2, 10.1, 9.9, 10.3, 9.8, 10.0 (product weights, g) | CV ≈ 1.86% | Excellent manufacturing consistency. Mean = 10.05 g, SD ≈ 0.187 g. |
| 25, 28, 22, 30, 24, 26, 25 (points per game) | CV ≈ 10.22% | Moderate performance variability. Mean ≈ 25.71 points, SD ≈ 2.63. |
How to Use the Coefficient of Variation Calculator
- Type or paste your data set into the Data Set field, separating values with commas, spaces, or line breaks.
- Ensure you have at least 2 numeric values — the sample standard deviation requires a minimum of two data points.
- Click Calculate. The calculator instantly displays the mean, sample standard deviation, and CV as a percentage.
- Use the example buttons to load pre-built data sets and see how the results change with different distributions.
- Click Reset to clear the field and start a new calculation.
Coefficient of Variation FAQ
What is a good coefficient of variation?
There is no universal threshold, but context matters. In laboratory assays, a CV below 5% is generally considered excellent and below 15% is acceptable. In finance, a CV below 10% often indicates a relatively stable asset. In manufacturing, targets depend on the tolerance specification for each part. Always benchmark against the relevant industry standard for your application.
What is the difference between CV and standard deviation?
The standard deviation is an absolute measure of dispersion expressed in the same units as the data. The CV is a relative measure, expressed as a percentage, that normalises the standard deviation by the mean. This makes CV dimensionless and allows valid comparisons across data sets with different units or scales — for example, comparing the variability of stock returns to the variability of reaction times.
When should I use population SD instead of sample SD?
Use sample standard deviation (dividing by n − 1) when your data is a sample drawn from a larger population and you want an unbiased estimate of the population dispersion — this applies to most scientific, engineering, and business scenarios. Use population standard deviation (dividing by n) only when your data set represents the entire population with no sampling involved, such as the scores of every student in a single closed class.
Can the CV be greater than 100%?
Yes. A CV above 100% indicates that the standard deviation is larger than the mean, which typically signals a highly heterogeneous or skewed distribution. This can arise naturally in data sets that include outliers, zero-inflated counts, or distributions with heavy tails. A CV well above 100% is a strong signal to investigate whether outliers are distorting the analysis.
Why is CV undefined when the mean is zero?
The CV divides the standard deviation by the mean. Division by zero is undefined mathematically. Conceptually, when the mean is zero, the notion of 'relative to the mean' loses meaning. In practice, if your mean is exactly or very close to zero, the CV is not an appropriate summary statistic; consider using the standard deviation alone or a different measure of spread.
Is the CV affected by outliers?
Yes. Both the mean and the standard deviation — and therefore the CV — are sensitive to outliers. A single extreme value can inflate the standard deviation substantially while shifting the mean, causing the CV to rise or fall dramatically. Before reporting a CV, it is good practice to inspect the data for outliers using a box plot or the interquartile range, and to report whether any values were excluded and why.