Ranges of outcomes
Read a fan of equity curves, and size for its bad edge. · 8 min
ProOpen to everyone while Pro is in preview.
One equity curve is a story. A fan of curves is the range of stories the same edge can tell: the middle line is the typical outcome, the outer lines the lucky and unlucky ones. Decisions belong to the outer lines.
Predict first
A strategy wins 40% at 2R, a true edge of +0.2R a trade. Risking 2% a trade, how likely is it to be behind after 100 trades?
Read the fan, then pick the risk
One hundred future trades drawn from a strategy’s results, 800 times. Five lines: the 5th, 25th, 50th, 75th and 95th percentiles.
Running the numbers…
How to read a fan
- Median (middle line): half the futures do better, half worse. Not a promise.
- 25th to 75th percentile (band): the ordinary range.
- 5th percentile: the bad case to plan for. One future in twenty is worse.
- Drawdown percentiles: the depth of the worst hole, which is what ends careers.
Worked example
At 1% risk the 1-in-20 drawdown is 12%. Your limit is 25%.
- For small risks, drawdowns grow roughly in proportion to risk.
- 25 ÷ 12 ≈ 2.1, so about 2% risk reaches the limit one time in twenty.
- Compounding makes deep drawdowns a little shallower than linear, but check: always re-run the fan at the chosen risk.
Common mistake
Planning on the median. The median is the outcome you are least likely to need a plan for. Risk is set by the 5th percentile, because that is the future that tests whether you keep trading.
Closing round
Size it from the fan
A strategy’s next 100 trades at 1% risk, 600 times.
Building a fresh case…
Open the expectancy Monte Carlo →
Further reading: Davey, Building Winning Algorithmic Trading Systems; Carver, Systematic Trading (on sizing for the bad case).