Skewness
Skewness is the third standardized moment of a return distribution, measuring its asymmetry around the mean — positive skewness indicates a distribution with a longer right tail (infrequent large gains), while negative skewness indicates a longer left tail (infrequent large losses) relative to a symmetric normal distribution. Skewness is a critical risk measure for hedge funds because standard deviation and VaR alone fail to capture the asymmetric loss profile characteristic of many alternative strategies.
Key takeaways
- Negative skewness is particularly dangerous for investors because it means extreme negative returns occur more frequently than a normal distribution would predict — 'picking up pennies in front of a steamroller.'
- Many hedge fund strategies — particularly short volatility, merger arbitrage, and fixed income arbitrage — exhibit negative skewness due to their asymmetric payoff profiles (steady small gains punctuated by occasional large losses).
- Investors should demand higher average returns from negatively skewed strategies to compensate for the increased tail-loss risk — failing to do so misprices the risk and leads to overallocation.
- The sample skewness estimator is unreliable with small samples (under 100 observations); bootstrap techniques or parametric assumptions should supplement it for robust estimation.
- Options markets explicitly price skewness through the volatility skew — the difference between implied volatility for out-of-the-money puts and calls reflects the market's pricing of left-tail risk.
Explanation
In finance, returns are rarely normally distributed, and the departures from normality — captured by higher moments like skewness and kurtosis — are often more economically significant than mean and variance alone. Skewness measures the degree of asymmetry in a distribution: a symmetric distribution (like the normal) has skewness of zero, a right-skewed distribution has a long right tail and positive skewness, and a left-skewed distribution has a long left tail and negative skewness.
For hedge funds and alternative investments, skewness carries profound implications for risk management and performance evaluation. Strategies that write options (short gamma, short vega), engage in carry trades, or provide liquidity during market stress tend to generate negatively skewed return streams. These strategies earn a 'skewness premium' — above-average Sharpe ratios during normal conditions — but at the cost of occasional severe drawdowns. The 2008 financial crisis exposed the true risk profile of many hedge funds that had been earning apparent alpha through implicit short-volatility exposure: what looked like skill-based excess returns were partly compensation for accepted tail risk.
Quantitatively, the population skewness is defined as the expected value of the cubed standardized deviation: γ₁ = E[(X - μ)³] / σ³. The sample estimator introduces bias for small samples, and corrections (such as the Fisher-adjusted estimator) are important in practice. For typical monthly return series of three to five years, the confidence intervals around skewness estimates are wide enough that distinguishing a modestly negative skew from zero requires many years of data. This statistical imprecision means investors often underestimate the negative skewness of strategies that have not yet experienced their tail events.
Alternative risk measures better capture skewness than standard deviation. Expected shortfall (CVaR) conditions on the worst outcomes and is naturally sensitive to left-tail thickness. The Sortino ratio addresses downside deviation specifically but does not capture the full distributional shape. Omega ratio and Calmar ratio offer complementary perspectives. In multi-asset portfolio construction, the correlation of skewness across positions is critical: if all strategies in a fund simultaneously exhibit negative skewness through common macroeconomic exposures (risk-off events), the aggregate portfolio skewness can be far more negative than any individual component.
In derivatives pricing, skewness manifests as the volatility skew (or 'smirk') in equity options: out-of-the-money puts trade at higher implied volatility than out-of-the-money calls, reflecting the market's premium for left-tail protection. Hedge fund managers who sell put options to enhance yield are explicitly selling skewness — receiving the skewness risk premium in normal times but absorbing the cost during market crashes. Understanding and pricing this risk requires going beyond mean and variance to explicitly model third and fourth moments.
Formula
Skewness (γ₁) = E[(X - μ)³] / σ³ = (1/n) × Σ[(xᵢ - x̄)³] / s³
Example
A hedge fund runs a short-volatility strategy writing S&P 500 put spreads. Over 36 months, it generates the following monthly returns (annualized): January through November average +1.2% per month with low standard deviation. In December of year three, the strategy loses 18% in a single month following an unexpected geopolitical shock. The three-year return series has a positive mean (+0.9%/month average) and modest standard deviation (3.2%/month), yielding an apparently attractive Sharpe ratio of 3.4. However, the sample skewness is -2.8 — severely negatively skewed. Had investors correctly priced the skewness risk by requiring an additional 3% annual return to compensate, the strategy would have appeared uneconomic. The Sharpe ratio masked the true risk profile that skewness, kurtosis, and maximum drawdown analysis would have revealed.
Related terms
Alpha Calmar Ratio Correlation Drawdown Equity Expected Shortfall Financial Crisis Gamma Greeks Hedging Hedge Fund Implied Volatility Kurtosis