Base rate

Do Donchian breakout rules work on US stocks (daily bars)? 13,377 backtests

By Justin JaegerPublished Updated

Donchian breakout rules on US stocks with daily bars were backtested 13,377 times (1,588 variants, 400 symbols) over the full history after retail costs. 14.1% beat cash and 6.4% beat buy-and-hold; the median Sharpe was −0.25. That makes them mostly negative even in hindsight.

Key numbers

MeasureValue
Backtests13,377
Distinct strategies1,588
Symbols400
Median Sharpe−0.25
10th to 90th percentile−0.59 to +0.05
Beat cash (Sharpe above 0)14.1%
Sharpe above 10.03%
Beat buy-and-hold6.4%
Median trades56
Of those with positive returns: still positive after 202353%

What it means

These are full-history results, the most favourable view a rule can get. If Donchian breakout rules lose here, they will not do better on new data. The best single variant looks much better than the median simply because it is the best of 1,588; compare any backtest you have with the median (−0.25) and the 90th percentile (+0.05), not with the top.

With and without filters

Each variant combines the rule with a macro or market filter (or none). By filter family:

Filter familyBacktestsMedian SharpeBeat cashBeat buy-and-hold
market data (VIX, indices, commodities)4,427−0.2316.8%7.5%
liquidity (money supply, balance sheets)1,790−0.2414.3%6.8%
macro releases (CPI, PMI, payrolls ...)2,263−0.2413.9%6.0%
interest rates and yield curve2,205−0.2613.2%5.7%
sentiment and surveys2,000−0.2711.9%5.8%
crypto market data692−0.397.1%4.2%

See the study Do macro filters improve technical trading rules?

By symbol

Symbols with at least 5 variants, best and worst by median Sharpe:

Best symbolsBacktestsMedian SharpeBeat cash
CEG32+0.7197%
META10+0.4590%
HII13+0.4092%
AXON16+0.3788%
BKR27+0.3685%
Worst symbolsBacktestsMedian SharpeBeat cash
CLX25−5.320%
ECL48−5.130%
CL42−4.610%
ORCL20−4.220%
COP58−4.220%

Other rules on US stocks, daily bars

Rule familyBacktestsMedian SharpeBeat cash
RSI zone rules14,056−0.2214.5%
Moving-average crossover rules9,339−0.2416.4%
Donchian breakout rules13,377−0.2514.1%
MACD crossover rules13,297−0.2712.0%
Bollinger squeeze rules10,247−0.730.9%

Same rule, other timeframes

TimeframeBacktestsMedian SharpeBeat cash
15-minute10,721−1.600.2%
daily13,377−0.2514.1%
1-hour11,315−0.812.4%
4-hour10,933−0.516.1%

Caveats

In-sample, not validated on new data: full-history backtests after retail costs, Sharpe minus a 4% cash rate. "Still positive after 2023" only counts variants with positive returns over the full history, which includes 2023–2026, and 2023–2026 were rising markets, so read it as an upper bound. Monthly macro filters were applied 1–3 weeks before publication in these backtests, which flatters them. Some price files had data errors.

Terms used: in-sample upper bound, trial count, dead end.

Before your next backtest

Let your AI check how ideas like yours did before it runs a single test. In our pilot, agents that checked first spent 1% of their backtests on known dead ends instead of 15%, and every backtest not wasted is time and tokens you keep. Cite this entry as ER-LIB-DONC-US-1D, as of 2026-11-01.

Related evidence

Questions

Do Donchian breakout rules work on US stocks with daily bars?

Donchian breakout rules on US stocks with daily bars were backtested 13,377 times (1,588 variants, 400 symbols) over the full history after retail costs. 14.1% beat cash and 6.4% beat buy-and-hold; the median Sharpe was −0.25. That makes them mostly negative even in hindsight.

How should I read my own backtest against this?

Compare it with the median (−0.25) and the 90th percentile (+0.05) of 13,377 comparable backtests, and count how many variants you tried. A top result among many tries is expected by luck.

Is this investment advice?

No. These are research statistics about a class of rules, not a recommendation.