Rank-Normalized Non-Gaussian Momentum

Family: trend_following · Regime: trending · Complexity: medium · Asset classes: Equities, Forex, Crypto · Timeframes: H1, H4

Thesis

Market returns are not normally distributed; by using the Jarque-Bera test to detect non-normality and Rank Correlation to ensure trend 'neatness,' we enter trades only when a trend is structurally distinct from noise, using psychological round levels as structural support/resistance.

Components

• EMA with Dynamic Length Switch Logic (regime) — Acts as a hyper-sensitive trend filter to ensure the current price is moving in the trade direction with minimal lag.
• Momentum (direction) — Provides the primary directional bias; ensures price difference over 10 periods aligns with the trade.
• Rank Correlation Index (entry) — Identifies when price trends exhibit high rank-order consistency (Spearman correlation), filtering out noisy, non-directional volatility.
• Average True Range (NNFX) (exit) — Determines the profit target relative to current market volatility to avoid exiting too early in high-range environments.
• Round Levels Zone Shading (risk) — Defines market structure context for risk; stops are placed behind psychological barriers where liquidity typically clusters.
• Jarque-Bera Test (JB) (volatility_filter) — Filters for non-normal price distributions. High JB values suggest 'fat tails' or trending surges that deviate from a Gaussian random walk.

Known failure conditions

• Jarque-Bera remains below 5.99 for extended periods (persistent Gaussian noise).
• RCI oscillates rapidly between +/- 50 without reaching extremes.
• Price repeatedly violates Round Level zones without following through (liquidity traps).

Explore the full interactive blueprint with parameter ranges and evidence on WOBR StrategyVerse, or generate this strategy as an MT4/MT5 Expert Advisor with QuantMogul AI Engine (free download).