Does ATR Expansion help RSI(2) Mean Reversion?
Crypto · 186 backtest runs · As of 31 Aug 2026 · Methodology
Not DecidableDSR ✗ not confirmed
Enough runs, but they disagree: the effect's 90% interval straddles the ±1 percentage-point line. Claiming a direction would assert more precision than the data supports.
CAGR Comparison
Baseline CAGR
0.6%
no filter
Filtered CAGR
3.4%
ATR Expansion
Δ CAGR
+1.38%
Sample
186
runs
Baseline Net CAGR
-0.1%
after costs
Filtered Net CAGR
2.8%
after costs
Risk-Adjusted Performance
Baseline Sharpe
0.051
median
Filtered Sharpe
0.248
Δ Sharpe
+0.15
DSR
21.6%
not confirmed
How does this filter work?
Signals only during ATR expansion (trend onset)
DSR Methodology
▼
DSR = PSR(SR̂₀) per Bailey & López de Prado (2014). SR̂₀ = 0.6610 (expected best Sharpe from 9 random filter trials).
Testing multiple filters on the same data increases the chance of finding a good result by luck. DSR measures whether this result clears the multiple-testing threshold. Pass threshold: DSR ≥ 90%. Current: 21.6%.
Full analysis in Edge Library
Per-asset breakdown, trade-level data, Sharpe comparison — available after sign-in.
← All edge reportsComputed 31 Aug 2026 · Methodology