Negative after costs

DOGEUSDT · 60m · Verdict Card

N-bar range breakout · breakout · hold 24 · 2025-06-01 → 2026-10-11 · 11929 bars · bybit · 2026-10-12 12:48

Rule: Long on a close above the prior 48-bar high, short on a close below its low
Cost model: 5.5bp/side fee + 3bp/side slippage + 0.07bp/bar funding

Trades

232

Win rate

42.7%

Avg / trade

-28bp

Gross avg

-9bp

Total

-6392bp

t-stat

-1.02

Permutation p

0.7001 · T0.700/S0.613

95% CI of mean

[-80bp, 30bp]

Max drawdown

51.7%

Exposure

56.1%

Profit factor

0.83

Worst trade

-1506bp

Median

-50bp

Equity curve (log)

Buy & hold: -55.3% · missing 0 (max gap 0) · OHLC complete

Stability by segment

Seg	From → To	Trades	Avg / trade	Win rate	t-stat
Seg 1	2025-08-25 → 2025-11-29	58	-52bp	43%	-0.75
Seg 2	2025-12-01 → 2026-03-13	58	14bp	50%	0.26
Seg 3	2026-03-16 → 2026-06-24	58	-59bp	38%	-1.50
Seg 4	2026-06-27 → 2026-10-08	58	-14bp	40%	-0.28

In-sample/Out-of-sample	Trades	Avg / trade	Win rate	t-stat
In-sample 60%	139	-35bp	43%	-0.93
Out-of-sample	93	-16bp	42%	-0.43

Trade log · last 12 trades

Time	Side	Entry px	Exit px	Bars held	Exit	Net
2026-10-08 12:00	SHORT	0.08732	0.08479	24	time	275.3bp
2026-10-07 02:00	SHORT	0.09429	0.08854	24	time	610.5bp
2026-10-05 01:00	LONG	0.09541	0.09465	24	time	-98.7bp
2026-10-03 02:00	SHORT	0.09101	0.09314	24	time	-250bp
2026-09-30 20:00	LONG	0.09727	0.09447	24	time	-310.8bp
2026-09-28 09:00	SHORT	0.0954	0.09261	24	time	278.1bp
2026-09-26 06:00	LONG	0.09927	0.09636	24	time	-316.2bp
2026-09-23 10:00	LONG	0.10341	0.09376	24	time	-998.3bp
2026-09-21 17:00	LONG	0.09211	0.09872	24	time	674.4bp
2026-09-20 16:00	SHORT	0.08473	0.09186	24	time	-826.6bp
2026-09-19 04:00	LONG	0.08826	0.08894	24	time	58.1bp
2026-09-18 00:00	LONG	0.08208	0.08772	24	time	645.9bp

Method & known limits

Exit: fixed 24-bar hold; fill=signal bar close
Costs: 5.5bp/side fee + 3bp/side slippage + 0.07bp/bar funding drag (same both sides; funding sign not modeled)
Non-overlapping: signals during open positions are dropped
Significance: t-stat on per-trade net returns. Two nulls — (1) timing permutation: entry times randomized, direction mix kept, same trade count, same non-overlap suppression, p=0.7001; (2) sign-flip permutation: each trade's realized move kept, direction re-rolled (variance-matched, stricter for fades), p=0.6127. Verdict uses the stricter p=0.7001 (2000 trials, seed 42, reproducible)
The null must match the live procedure trade-for-trade: every surrogate fills the same count (232 entries, 2000 effective trials). A surrogate that only fills ~9 entries widens the null about 4x and can fake p=0.30 out of p=0.01
Uncertainty: mean 95% bootstrap CI [-80bp, 30bp] — spanning 0 means no claim of edge
Sample: 11929 bars of 60m, 0 missing (max gap 0), OHLC complete
Splits: first 60% in-sample, rest out-of-sample, plus 4 time blocks to catch single-segment flukes
Params: lookback=48 side=both warmup=2000 — if tuned on this same history the verdict carries selection bias; collect out-of-sample before believing it
Known limits: no order-book depth so slippage is assumed; liquidation/margin/liquidity not modeled; rejected or partial fills not modeled
Null sensitivity: the sign-flip test keeps each trade's realized move and re-rolls only the direction, so the long/short allocation itself counts as evidence — in a one-way market that can inflate significance. Hence the verdict requires both nulls to clear, a positive net mean and a positive out-of-sample mean; miss one and it degrades to "not separated from luck"

This card only judges whether a rule has statistical evidence under stated costs. Not investment advice; past results do not predict future returns.