Rejected thesis
Cross-sector momentum
Thesis (marginal): Rank the 11 SPDR sector ETFs by 6-month return; top-ranked sectors continue to outperform bottom-ranked sectors over the next 1-6 months. Classical sector-level momentum (Asness 1997).
Code: research/cross_sector_momentum_validate.py
Report: research/cross_sector_momentum_report.json (n=498)
Why we're parking it: Edge is in the right direction (top beats bottom) but small and only marginally significant.
| Horizon | Top mean | Bot mean | Spread | t-stat |
|---|---|---|---|---|
| 21 d | +1.11 % | +1.04 % | +0.06 pp | +0.11 |
| 63 d | +3.24 % | +2.45 % | +0.79 pp | +0.87 |
| 126 d | +7.00 % | +4.84 % | +2.16 pp | +1.71 |
Sector momentum exists but the magnitude doesn't justify a single-name position. It works as a portfolio overlay (long top 3 sectors via ETF basket, rebalance monthly) but doesn't generate per-name watch-list signals.
Verdict: Not added. Reasonable passive overlay, not a watch-list trade.
| Sample | 498 |
|---|---|
| Validator | research/cross_sector_momentum_validate.py |
| Verdict | Rejected |
Every result here is reproducible from the script named above. Reports are in the repository.
- Volatility squeeze
- Pre-FOMC drift
- Uptrend pullback
- Momentum continuation
- Industry-relative momentum (at 4-week lookback)
- Earnings-reaction reversal (anti-PEAD)
- Beat-persistence pre-earnings drift
- Sector ETF mean-reversion
- 52-week-high breakout
- Volume accumulation (above-200DMA +...
- Analyst-upgrade cluster
- PEAD × sector tailwind (combination)