20 — Volatility

Standard Deviation#

✓ Mathematical
◆ The Patternσ = √(Σ(x−μ)²/N).

Standard Deviation — the statistical building block of volatility measurement.

σ = √(Σ(x − μ)² / N)
where μ = mean, N = number of observations

Higher σ = more volatility = prices are spread far from the mean.

In markets:
• Historical Volatility = σ of returns × √252 (annualized)
• 1σ covers ~68% of observations
• 2σ covers ~95% → basis of Bollinger Bands
• 3σ events are "rare" but happen more often in markets than normal distributions predict (fat tails)
Pattern bridge: This is standard deviation from statistics, applied to price returns. In ML, it’s the denominator in batch normalization and the width of Gaussian distributions.
← Previous
Donchian Channels
Open in the full reader, with the topic sidebar →