Evidence & Calibration
Sample size, expectancy, overfitting, and how to tell a real edge from a story told about noise.
This is the reasoning the product itself runs on — the sample floors, the refusal to publish thin numbers, the difference between a hit rate and an expectancy. It is placed late because it is the track that lets a student audit everything earlier, including us.
- 1Win rate is not edgenot written yet
Build a losing system with a 70% win rate.
Checkpoint: Size the trade - 2Expectancy, and how to compute yoursnot written yet
One number that survives a bad week.
Checkpoint: Size the trade - 3How large a sample do you neednot written yet
Why twenty trades tells you almost nothing.
Checkpoint: — - 4Calibration: saying 70 and being right 70%not written yet
Score your own confidence against outcomes.
Checkpoint: Call the grade - 5Overfitting, in one chartnot written yet
Watch a rule get better and more useless at once.
Checkpoint: Spot the trap - 6Survivorship and the screenshot problemnot written yet
Why every strategy looks profitable on social media.
Checkpoint: Spot the trap - 7Reading a backtest without being sold onenot written yet
The five questions that break most of them.
Checkpoint: Sequence - 8Auditing ORINnot written yet
Use the published record to check the tool that taught you.
Checkpoint: —
The concepts here are applied in the Trade Playbook, and the engine that grades them is taken apart in how AI chart analysis works.