Whether a performance measure holds up across sub-periods, which separates a durable edge from one that worked in a single regime.
Split the record into halves or thirds and recompute expectancy-per-trade, win-rate and payoff-ratio in each. Stable figures across periods are evidence of something real; figures that were strong in one stretch and flat afterwards describe a regime, not an edge.
Do the same across instruments and conditions. A strategy that works only in high-volatility environments is not broken - it is conditional, and knowing the condition lets you trade it deliberately rather than wondering why it stopped. That is a question about regime filters rather than a failure.
Beware of over-reading the split, though: each half has half the sample, so differences of 5-10 percentage points in win rate between halves are entirely expected. Compare the difference against the standard-error-of-expectancy before concluding anything decayed.
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.