How much of a strategy's profit comes from a handful of trades, which determines how repeatable the record really is.
Rank every trade by profit, remove the top 5%, and recompute expectancy. If a plus 0.30R edge becomes minus 0.02R, the strategy is an outlier-harvesting machine and should be understood as such.
That is not automatically bad. Trend following, venture-style position building and long-option strategies are designed to be outlier-dependent, and their practitioners accept long flat stretches as the cost. The failure is mismatching behaviour to design: taking profits at plus 1R in a system whose edge lives past plus 5R converts a profitable strategy into a losing one while every individual decision feels prudent.
It also changes the evidence standard. Outlier-dependent strategies need far more trades before their statistics mean anything, because the mean is dominated by rare events that a short sample may contain zero or three of, purely by luck.
Original diagrams for the ideas on this page. Illustrative, not real market data.
Expectancy: the average trade. Forty trades sorted by outcome: 24 small losses and 16 larger wins. Weighting each side by how often it happens gives the average result per trade, marked here by the dashed line at +$120.
Educational only, not advice. Spotted an error? Post in Site Feedback.