RESEARCH · 2026-09-11
Rotation as a 2–3 day directional warning
FALLEN Fallen — broke its own criteria; kept on purpose
Hypothesis and result
Ten rotation states (gold vs equities, bonds vs equities, defensive vs cyclical, energy vs tech, semiconductors vs broad, dollar up/down, silver leading gold, everything down, flight to safety) tested against eight instruments on two horizons.
Rotation describes the day; it does not predict the next two.
The evidence card
| Sample | 160 tests · 1252 days of data |
|---|---|
| Effect | 0 of 160 tests survive |
| Half-split test | Not recorded on the card — see the result text above. |
| Multiple-testing status | Not judged on p — the finding is assessed on hit rate, half-split and forward shadow. |
| Stage | Fallen — broke its own criteria; kept on purpose |
| Re-measured | Re-measured when its source script is run — no schedule · last 2026-09-11 |
What would invalidate it
- a state gives more than 55 % over baseline with n ≥ 40 and a passing half-split on 180 new days
How to read this page
Every number describes the past under the stated conditions. A finding that passes today can fall tomorrow; Apex keeps fallen findings visible on purpose. Stages, tests and the family-wise correction are described in the methodology.