The blog
Long-form posts on testing trading ideas honestly: telling a real edge from luck, how many trades a backtest needs before it means anything, and why a perfect backtest is the most suspicious kind. Plain English, real numbers, no hype.
The better your backtest looks, the more suspicious you should be. Here is the mechanism that makes perfect results easy to manufacture, and the defenses that actually reduce the damage.
Read it →Your backtest is not lying to you. It is answering a different question than the one you asked.
Read it →A 20-trade backtest with a 65% win rate is compatible with a coin flip. Here is the actual math for how many trades you need before your numbers mean anything.
Read it →A 60% win rate over 20 trades is statistically indistinguishable from a coin flip. Here's the math that proves it.
Read it →Theory into practice
Spawn a variant, run it on the same engine, and read the edge-significance verdict yourself.