Glossary term
Coefficient of Variation (CV)
The coefficient of variation measures relative variability by dividing standard deviation by the mean, often shown as a percentage.
Updated
Read time
What Is the Coefficient of Variation?
The coefficient of variation, or CV, measures relative variability by comparing standard deviation with the mean. It shows how large the typical variation is relative to the average level of the data.
In finance, CV can help compare risk per unit of expected return or variability across data series with different scales. It is most useful when the mean is positive, meaningful, and comparable across the items being analyzed.
Key Takeaways
- CV equals standard deviation divided by the mean.
- It expresses variability relative to the average level of the data.
- A higher CV means more variability per unit of mean.
- It can help compare data series with different scales.
- It can mislead when the mean is near zero, negative, or not economically meaningful.
Formula
The basic population formula is:
In this expression, σ is the standard deviation and μ is the mean. Analysts often multiply the result by 100 to express CV as a percentage. For sample data, the sample standard deviation and sample mean are commonly used.
If an investment has an expected return of 8 percent and a standard deviation of 12 percent, its CV is 1.5. That means the standard deviation is 1.5 times the expected return.
How Investors Use It
Investors may use CV to compare the volatility of investments relative to their expected returns. Two investments can have the same standard deviation but different expected returns, making one look more efficient on a relative basis.
For example, an asset with a 10 percent expected return and 15 percent standard deviation has a CV of 1.5. An asset with a 5 percent expected return and 15 percent standard deviation has a CV of 3.0. The second asset has the same absolute volatility but more volatility per unit of expected return.
What It Shows
CV reading | General interpretation |
|---|---|
Lower CV | Less variability relative to the mean |
Higher CV | More variability relative to the mean |
Near-zero mean | CV may become unstable or meaningless |
CV is especially useful when comparing things measured in different units or with different average levels, such as return series, cost variability, process data, or operating metrics.
Where CV Can Mislead
CV depends heavily on the mean. If the mean is close to zero, a small change in the denominator can make CV explode. If the mean is negative, the interpretation can become awkward because the ratio may not reflect intuitive relative risk.
For investment returns, CV should not replace other measures such as Sharpe ratio, maximum drawdown, downside deviation, beta, or scenario analysis. Standard deviation treats upside and downside variation symmetrically, while investors usually care more about losses.
CV Versus Standard Deviation
Standard deviation measures absolute variability in the same units as the data. CV standardizes that variability by the mean. That makes CV helpful when scale differs, but standard deviation is still important when the absolute size of risk matters.
A low CV on a very large exposure can still represent meaningful dollar risk. A high CV on a tiny exposure may be unimportant to the total portfolio.
Practical Reading
The best use of CV is comparative. It helps ask whether one data series is more variable relative to its average than another. It is less useful as a stand-alone quality score.
In portfolio work, CV should be paired with the investor's objective. A retiree managing drawdown risk, a trader managing daily volatility, and a company comparing process stability may each care about different forms of variability.
The Bottom Line
The coefficient of variation measures relative variability by dividing standard deviation by the mean. It is useful for scale-adjusted comparisons, but it must be handled carefully when means are low, negative, or not economically meaningful.