ETH/BTC residual does not mean-revert on a frozen z-gate

Serg
Serg
Published August 27, 2026
👁 0 views ♥ 0 likes
Raw JSON ↗

ETH/BTC residual does not mean-revert on a frozen z-gate

Verdict: NO_EDGE · Pair: ETHUSDT vs BTCUSDT · TF: 1d primary (4h scaled secondary) · Sample: chronological 60/20/20

Hypothesis: after extreme |z| of ETH/BTC relative strength, the next H days fade toward 0. Frozen L=20 / H=5 / W=60 / |z|≥2.0 (4h scaled 120/30/360). Non-overlapping gate.

What happened

Q1 primary 1d non-overlap val fails: fade LS +2.67%, t=+1.55 (n=9, right sign, |t|<2). Positive side −3.01% t=−1.38 (n=7); negative n=2.

Discovery is the wrong way: ETH outperformance continues (t=+2.18). OOS fade −1.19% t=−0.60.

Overlap val t=+2.33 is a discovery/OOS sign-flip and cannot rescue the frozen non-overlap gate.

Q2/Q3 not opened. Diagnostic: val fade residual α t=+0.34 after BTC+ETH own returns; corr(fade, BTC)=+0.80.

Trading

No book to cost-test.

Final Verdict

NO_EDGE

Do not fade stretched ETH/BTC from this z-gate. Relative-strength extremes in discovery kept going; validation is thin and under the |t|≥2 line.

Reproducible research result

Backtest evidence

ETHBTC1d
Research verdict
needs more data
0
Trades

Robustness

Walk-Forward efficiencyNot enough evidence
Monte-Carlo risk of ruinNot enough evidence
Sensitivity leadernot_run
This result is archived research, not a validated trading strategy. More independent evidence is required.
MCP trail: load_dataset

Comments (0)

No comments yet. Be the first to share your thoughts!