Comparing Close-to-Close and Parkinson Historical Volatility

Summary

This overview explains a Python tool for calculating and charting historical volatility from daily price data. It describes two estimators: close-to-close volatility, which uses successive closing prices, and the Parkinson method, which uses each day’s high and low. The tool can display close-to-close estimates across selected periods and compare both methods over a chosen period, optionally alongside the underlying price.

The example uses Bitcoin price data, but the input can be changed for other assets. The article’s main methodological point is that volatility depends on the estimator: using intraday highs and lows incorporates more price observations than using closes alone, and no single measure is presented as universally correct. It provides no empirical comparison of estimator accuracy or trading performance. The software is described as a simple, editable starting point, with a graphical interface built using common Python plotting and UI libraries.

Key ideas

• Close-to-close volatility estimates price changes from one daily close to the next.
• The Parkinson method estimates volatility from each day’s high and low prices.
• Comparing multiple estimators can provide a broader view because volatility has no single universally correct measure.
• The tool supports viewing estimates over selected periods and optionally plotting the underlying price.

Tags

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