VII · Hypothesis
Station VII of The Quant Map: if mechanism X is real, feature F should predict Y over horizon H. Falsifiable claims. Reading order plus the free map PDF.
“if mechanism X is real, feature F should predict Y over horizon H”
Write the death condition before the run. "Ranked by carry-to-volatility, the top third of G10 beats the bottom third over the next one to three months, after costs" can die: the buckets fail to rise in order, or the whole result lives in 2002 to 2007. "This chart looks like a head and shoulders" cannot die. Explanation is cheap after the print. A prediction is a dated, specific claim you cannot edit. The scientific bar is the pre-commit: hypothesis, null, statistic, threshold, held-out window, trial count, in a file whose timestamp is earlier than the result.
A hypothesis is a dated, specific claim that can die. Write the death condition before the run, in a file whose timestamp is earlier than the result.
The Quant Map PDF works this spine through example research: five full descents from observation to live rule, and a library of 835 strategy entries, each with a named payer and a named failure mode. Get the free PDF on the Start Here page.
Reading order
Top to bottom. Stop at the first article you cannot apply to a live trade; that is the one to read slowly.
| Article | Why it is on this row |
|---|---|
| Technical Analysis as a Scientific Hypothesis | The rule, the statistic, the null, the threshold, written first. A popular moving-average cross on SPX often fails to clear 0.05. |
| How to Make Technical Analysis Falsifiable | Turn the pattern into a function, a horizon, a success count, and a baseline. Then publish the rejection. |
| The Null Hypothesis for Trading Systems | Start from "no predictive power on detrended data." A rule that has not beaten that is a candidate. |
| The Difference Between Explanation and Prediction in Markets | A story fitted after the close had the answer. A forecast did not. Keep a dated log if you want the second. |
| The Scientific Method for Building Trading Systems | Eleven gates. A fail at any one stops the ship. Stacking them is how you buy a lower false-positive rate. |
| Induction in Trading: Why Past Patterns Are Always Uncertain | The hit rate has a confidence interval, and the interval still assumes the future rhymes. Regime quality is the part the interval ignores. |
On the map: ← VI · Feature engineering · The grand map · VIII · Validation →