Why the Sharpe ratio is not enough: measuring tail risk with Omega, Ulcer Index, SQN and Half-Kelly
The Sharpe ratio assumes Gaussian returns and penalises upside breakouts as risk. Here are the institutional metrics that actually measure drawdown stress and trade quality.
The Sharpe ratio was designed for diversified quarterly portfolios with near-normal return distributions. Crypto and active equity strategies look nothing like that: returns are skewed, tails are fat, and a single upside breakout candle increases standard deviation — which perversely lowers your Sharpe ratio.
Short answer: evaluate strategies across five complementary dimensions instead of one number: Omega Ratio for the full gain/loss distribution, Ulcer Index & Martin Ratio (UPI) for drawdown depth and duration, Van Tharp SQN for trade-by-trade consistency, and Half-Kelly for position sizing.
What each metric catches that Sharpe misses
| Metric | Formula / Definition | What it tells you | ||
|---|---|---|---|---|
| Omega Ratio | $\sum R^+ \div \sum | R^- | $ | Ratio of all probability-weighted gains to losses across the entire distribution, including fat tails. Above $1.25$ is solid. |
| Ulcer Index | $\sqrt{\frac{1}{N}\sum D_t^2}$ | Root-mean-square of drawdown depth across every bar spent below the high-water mark. Captures both how deep and how long you stay underwater. | ||
| Martin Ratio (UPI) | $\text{CAGR} \div \text{Ulcer Index}$ | Annualised return per unit of drawdown stress. | ||
| Van Tharp SQN | $\sqrt{N} \cdot \mu_R \div \sigma_R$ | System Quality Number: rewards strategies that produce steady expectancy across a large trade sample ($>1.6$ workable, $>2.5$ strong). | ||
| Half-Kelly (%) | $\frac{1}{2}\left(W - \frac{1-W}{\text{Payoff}}\right)$ | Conservative capital allocation derived from Win Rate ($W$) and Payoff Ratio, cutting full-Kelly drawdown volatility in half. |
Measured example: Volatility Squeeze vs. Stat-Arb Pullback
On 1,000 daily BTCUSDT candles:
- TTM Squeeze + SuperTrend Volatility Expansion delivered +58.90% net return, 1.60 Profit Factor, Omega 1.19, and SQN 1.41.
- WaveTrend + Z-Score Stat-Arb Pullback delivered +16.47% net return with an Ulcer Index of just 9.88% — lower total return, but far gentler underwater time.
In Strategy Studio, you can now select Omega, Ulcer (UPI), SQN or Calmar directly as your parameter optimisation objective.
This is research, not investment advice.
Evident does not give investment advice. Past performance does not indicate future returns. Leveraged and automated trading carries the risk of losing capital.