OPEN-SOURCE SCRIPT
Hurst Exponent DFA
This script computes the Hurst exponent using Detrended Fluctuation Analysis (DFA) in TradingView. It works as follows:
- It takes a user-defined lookback window of closing prices and centers them by subtracting their mean.
- It builds a cumulative profile of these centered values.
- For each sample size input by the user, it divides the profile into non-overlapping segments, fits a local linear trend in each segment, and measures the root-mean-square fluctuation around that trend.
- It then performs a log–log regression of the average fluctuation versus segment size to estimate the Hurst exponent H.
- An optional exponential moving average smooths the Hurst series to reduce noise.
- A horizontal line at H = 0.5 helps distinguish trending regimes (H > 0.5) from mean-reverting regimes (H < 0.5).
- It takes a user-defined lookback window of closing prices and centers them by subtracting their mean.
- It builds a cumulative profile of these centered values.
- For each sample size input by the user, it divides the profile into non-overlapping segments, fits a local linear trend in each segment, and measures the root-mean-square fluctuation around that trend.
- It then performs a log–log regression of the average fluctuation versus segment size to estimate the Hurst exponent H.
- An optional exponential moving average smooths the Hurst series to reduce noise.
- A horizontal line at H = 0.5 helps distinguish trending regimes (H > 0.5) from mean-reverting regimes (H < 0.5).
開源腳本
本著TradingView的真正精神，此腳本的創建者將其開源，以便交易者可以查看和驗證其功能。向作者致敬！雖然您可以免費使用它，但請記住，重新發佈程式碼必須遵守我們的網站規則。
免責聲明
這些資訊和出版物並不意味著也不構成TradingView提供或認可的金融、投資、交易或其他類型的意見或建議。請在使用條款閱讀更多資訊。
免責聲明
這些資訊和出版物並不意味著也不構成TradingView提供或認可的金融、投資、交易或其他類型的意見或建議。請在使用條款閱讀更多資訊。