RESEARCH · 2026-09-09
LONG/SHORT asymmetry
FALLEN Fallen — broke its own criteria; kept on purpose
Hypothesis and result
LONG appeared to beat SHORT by 2.1 percentage points.
A small difference that does not hold in both halves is noise with a sign.
The evidence card
| Sample | stated in the result above |
|---|---|
| Effect | +2.1 pp; fails the half-split |
| Half-split test | Fails — the sign does not hold in both halves. |
| 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 2026-09-09 |
What would invalidate it
- the gap holds in both halves on 300 new trades
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.