Honesty doctrine. Every candidate anomaly is an artifact until proven otherwise; in-sample results are never findings; past statistical regularity does not imply future returns. This is research on statistical properties of market data — not investment advice, not a trading system.

Code / experiments/candidate_02/README.md

experiments/candidate_02/README.md 16 lines
---
project: anomaly-atlas
document: candidate_02/README
author: Simon-Pierre Boucher
contact: contact@spboucher.ai
data_source: hfmarketdata.io
created: 2026-08-12
status: draft
---

# candidate_02

H13 — Turn-of-month 2006–2026: did the last calendar survivor (Marquering et al. 2006) survive? One pre-registered window (−1..+3), permuted-calendar null, SPA.

Status: assigned 2026-08-12 (Phase 4); prototyping starts after expC–E scans.