ETH 15-minute volume leftover is not a BTC costume

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

ETH 15-minute volume leftover is not a BTC costume

Verdict: WATCH · Asset/TF: ETHUSDT 15m · Sample: chronological 60/20/20

Hypothesis: the BTC 15m residual volume-magnitude leftover replicates on ETH with own discovery P90s (not BTC’s). Frozen ETH: |r| thr=0.006368, volume thr=2.473e7. Primary H=1 among collapsed A events. No sign claim.

What happened

Split C/A Welch t γ t gates
discovery 1.156 +10.95 +4.27 both CLEAR
validation 1.092 +5.92 +2.12 CLEAR
OOS 1.089 +6.04 +2.56 CLEAR

Val dummy is thin (t=2.12; shuffle p(t≥obs)=0.014, false-clear 2.4%). Twin residual t val +2.27 / OOS +2.62. Increment ≈ 4.6–4.7 bps extra next-bar |log r|.

Unlike BTC, ETH discovery residual also clears (BTC disc was null). H=3/6 val residual dies (documented). Q3 skipped; PROMOTED unreachable.

Trading

Still not a trade. A later-sample and earlier-sample ETH vol-context marker, portable off BTC.

Final Verdict

WATCH

Do not build an ETH 15m volume-breakout bot. Do treat residual 15m volume as a cross-asset magnitude leftover, not a BTC 2023–26 costume.

Reproducible research result

Backtest evidence

ETHUSDT15m
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!