Glossary term
Skewness
Skewness measures the asymmetry of a distribution, showing whether observations have a longer or heavier tail on one side.
Updated
Read time
What Is Skewness?
Skewness is a statistical measure of asymmetry in a distribution. It helps describe whether observations are balanced around the center or pulled toward one side by a longer or heavier tail. A distribution with positive skew has a longer right tail. A distribution with negative skew has a longer left tail.
Skewness matters in finance because returns are often not perfectly symmetric. Two investments can have the same average return and standard deviation but very different tail behavior. One may have frequent small gains and rare severe losses. Another may have frequent small losses and rare large gains. Skewness helps describe that shape.
Key Takeaways
- Skewness measures distribution asymmetry.
- Positive skew means the right tail is longer or heavier.
- Negative skew means the left tail is longer or heavier.
- Skewness complements mean, median, standard deviation, and kurtosis.
- In investing, skewness can reveal return patterns that average return alone hides.
Formula
In this common sample-style expression, Yi represents each observation, Ȳ is the average, s is the standard deviation, and N is the number of observations. The cubed deviations preserve direction, so large observations on one side of the mean affect the sign and size of skewness.
How To Read Skewness
A skewness value near zero suggests the distribution is roughly symmetric, though zero skewness does not guarantee a normal distribution. Positive skew suggests more extreme outcomes on the upside than the downside. Negative skew suggests more extreme outcomes on the downside than the upside.
In portfolio analysis, positive skew can be attractive when investors value upside optionality. Venture capital, trend-following strategies, and out-of-the-money options can have positively skewed payoff profiles. Negative skew can be dangerous when a strategy appears stable until a rare loss arrives. Selling insurance, selling options, or using hidden leverage can create negatively skewed returns.
Investment Context
Skewness helps explain why averages can mislead. A strategy that earns 1% most months but occasionally loses 20% may have a pleasant average for a while and still carry severe left-tail risk. A strategy that loses small amounts often but occasionally earns very large gains may look frustrating in normal periods but provide crisis or convex payoff potential.
Investors should not read skewness alone. A highly positively skewed investment can still have poor expected returns. A negatively skewed investment can be acceptable if the premium is large enough, risk is controlled, and the investor can survive the tail event. Skewness is a shape descriptor, not a full decision rule.
Example
Consider two funds with the same 8% average annual return. Fund A has mostly moderate results with few extreme years. Fund B gains 12% in most years but occasionally loses 35%. Fund B may have more negative skew even though the average return matches Fund A. That matters for investors who cannot tolerate large drawdowns.
Skewness is also sensitive to outliers and sample size. A few unusual observations can dominate the statistic, especially in small samples. That is why analysts often pair skewness with a histogram, percentile table, drawdown analysis, or scenario review.
In wealth planning, skewness has a practical translation: what kind of surprise can hurt the plan? A retiree may fear negative skew because one large loss early in retirement can damage withdrawal sustainability. A younger investor may tolerate more downside asymmetry if the potential upside is large enough and position size is controlled.
The direction of the tail is the practical clue.
The Bottom Line
Skewness shows which side of a distribution carries the tail. For investors, it helps reveal whether risk is mostly ordinary volatility, rare downside exposure, or upside optionality that standard deviation alone may not capture.