Skewness is a statistic that measures how lopsided a distribution of returns is. It captures whether the outcomes spread out more on one side of the average than the other, telling an investor whether the rare big moves are more likely to be losses or gains.

A perfectly symmetric distribution, such as the normal bell curve, has zero skewness: its left and right halves mirror each other. Real return data rarely behaves this neatly. Skewness puts a single number on the asymmetry, and the sign of that number reveals which tail is the longer one, which is information that average and spread alone cannot provide.

Definition

Skewness is the third standardized moment of a distribution, a formal way of summarizing the asymmetry of its shape. The first two moments describe the center (the mean, or average) and the spread (the variance, whose square root is the standard deviation). The third moment builds on these to describe the tilt: it measures how far and in which direction the distribution leans away from symmetry.

The sign carries the key message. Negative skew means a longer left tail, so the distribution has a string of small gains balanced against the possibility of a few large losses. Positive skew means a longer right tail, with frequent small losses offset by the chance of a few large gains. The size of the number indicates how pronounced the tilt is, while a value near zero indicates a roughly symmetric shape.

How It Works

The calculation compares how returns deviate from their average on each side. Each deviation is cubed before being averaged, and cubing preserves the sign of the deviation: a large negative deviation contributes a large negative term, while a large positive deviation contributes a large positive one. Dividing the result by the cube of the standard deviation puts the figure on a scale that does not depend on the units of measurement, so distributions of different sizes can be compared directly.

Because the deviations are cubed, the most extreme observations dominate the result. A single very large loss in an otherwise tame set of returns can pull skewness strongly negative. This sensitivity is the reason skewness reveals the influence of rare events that ordinary average and spread measures tend to mask, but it is also the reason the statistic can swing on the strength of a few data points.

Interpretation

For investors, negative skew tends to draw the most attention because its long left tail points toward the severe losses that tail risk analysis focuses on. Many strategies that earn steady returns most of the time carry hidden negative skew, since the same structure that produces frequent small gains can expose the holder to an infrequent but deep loss. Recognizing this asymmetry helps explain why two strategies with the same average return and the same standard deviation can still differ sharply in their risk of a damaging outcome.

Why Skewness Matters in Finance

Skewness matters because the common summary measures of return treat the upside and downside as equivalent, and investors do not. Variance and standard deviation count a gain and a loss of the same size as identical contributions to risk, which buries the question of which direction the extreme moves tend to run. Skewness restores that information by separating the long tail from the short one.

This distinction connects skewness to downside-focused tools. The Sortino ratio, for instance, penalizes only downside movement rather than all movement, reflecting the same intuition that negative surprises deserve more weight than positive ones. Skewness also informs how much trust to place in a measure like Value at Risk (VaR), since a strongly skewed distribution can hide loss potential that a symmetric model would miss.

Known Limitations

Academic Background

Skewness has long been part of statistics as the third moment of a distribution, but its role in finance grew as researchers questioned the assumption that returns follow a symmetric normal curve. Studies through the 1970s and 1980s documented persistent asymmetry in stock returns and debated which statistical models most faithfully captured it. This work established that ignoring skewness could lead investors to misjudge the balance between upside and downside in a strategy.

Later asset-pricing research extended the idea further, asking whether investors demand extra return for holding assets with unfavorable skew. Campbell Harvey and Akhtar Siddique's study of conditional skewness argued that the tilt of the return distribution helps explain how assets are priced, moving skewness from a descriptive statistic toward a factor in expected returns.

Further Reading

• Kon, S.J. (1984). "Models of Stock Returns: A Comparison." The Journal of Finance, 39(1), 147–165.
• Harvey, C.R. and Siddique, A. (2000). "Conditional Skewness in Asset Pricing Tests." The Journal of Finance, 55(3), 1263–1295.
• Kraus, A. and Litzenberger, R.H. (1976). "Skewness Preference and the Valuation of Risk Assets." The Journal of Finance, 31(4), 1085–1100.

Related Terms