Sample size, in the only terms that matter

People ask "how much data do I need" and the answer depends entirely on how noisy the thing you're measuring is. Rough intuition: the noisier the outcome, the more observations you need to see the signal through it. A strategy with a small edge and big variance needs far more trades to distinguish from luck than one with a large edge and tight outcomes. Practical version: if removing any single trade meaningfully changes your conclusion, your sample is too small. That test needs no statistics and catches most of the cases.