Normalizing Returns by Daily Range to Study Trading Signals

Summary

This short note poses two linked research questions: why dividing daily returns by the daily trading range might reduce fat tails and produce a distribution closer to Gaussian, and whether that transformed distribution could help identify trade entries. It points toward a volatility-scaled view of returns, in which a move is assessed relative to that day's range rather than in raw price units.

The document provides no derivation, dataset, empirical result, entry rule, or risk management procedure. It does not establish that the transformation consistently removes fat tails or that near-normal behavior holds across assets and market regimes. Any practical use would require testing the distributional claim and specifying how normalized observations translate into signals, exits, and costs. The material is a useful question for statistical investigation, but it does not itself offer a validated strategy.

Key ideas

• The note asks whether dividing daily returns by the day's range makes their distribution less heavy-tailed.
• It raises the hypothesis that range-normalized returns may be approximately Gaussian.
• It asks whether the transformed distribution can inform trade entry decisions.
• No derivation, empirical evidence, or executable entry and risk rules are supplied.

Tags

# How to trade risk-adjusted returns?


# How to trade risk-adjusted returns?












Why does dividing daily returns by daily range eliminates fat tails and results in an (almost) gaussian distribution? And how could that distribution be exploited to enter trades?

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.