# The Cross-Sectional Intrinsic Entropy. A Comprehensive Stock Market Volatility Estimator

**Authors:** Claudiu Vinte, Marcel Ausloos  
**arXiv:** [2205.00104](https://arxiv.org/abs/2205.00104)  
**Date:** 2022-04-29  
**Summary page:** https://www.summarizepaper.com/en/paper/2205.00104v1/

## Key points

- Claudiu Vinte and Marcel Ausloos introduce the cross-sectional intrinsic entropy (CSIE) model for estimating stock market volatility.
- CSIE model incorporates the temporal dimension of uncertainty and computes daily volatility estimates for the entire market based on OHLC prices and traded volume of symbols listed on NYSE and NASDAQ.
- Comparative analysis shows that CSIE market volatility estimator is significantly more sensitive to market changes compared to traditional estimators like close-to-close, Parkinson, Garman-Klass, Rogers-Satchell, Yang-Zhang, and intrinsic entropy (IE).
- The increased sensitivity of CSIE model is consistently observed to be at least 10 times higher than traditional volatility estimates captured through market indices.
- Analysis spanning from January 1st 2001 to January 23rd 2022 reveals lower volatility risk for market indices compared to the overall market based on beta values.
- Variance of CSIE market volatility estimates is shown to be on average 10 times higher than historical volatility estimates for DJIA across all considered time intervals and rolling windows.
- The study highlights the effectiveness of the CSIE model in capturing market dynamics and its potential utility in enhancing risk management strategies within stock markets.

## Summary

In their paper titled "The Cross-Sectional Intrinsic Entropy: A Comprehensive Stock Market Volatility Estimator," Claudiu Vinte and Marcel Ausloos introduce a novel approach to estimating stock market volatility by incorporating the temporal dimension of uncertainty. The proposed cross-sectional intrinsic entropy (CSIE) model computes daily volatility estimates for the entire market based on the open, high, low, and close prices (OHLC), along with the daily traded volume of symbols listed on the NYSE and NASDAQ. Through a comparative analysis with various historical volatility estimators such as close-to-close, Parkinson, Garman-Klass, Rogers-Satchell, Yang-Zhang, and intrinsic entropy (IE), derived from historical OHLC daily prices of major indices like S&P500, DJIA, and NASDAQ Composite index, the authors demonstrate that the CSIE market volatility estimator is significantly more sensitive to market changes. This increased sensitivity is consistently observed to be at least 10 times higher than traditional volatility estimates captured through market indices. By analyzing approximately 6000 day reference points spanning from January 1st 2001 to January 23rd 2022 for both NYSE and NASDAQ markets,Vinte and Ausloos also reveal that beta values confirm a lower volatility risk for market indices compared to the overall market. The variance of CSIE market volatility estimates is shown to be on average 10 times higher than historical volatility estimates for DJIA across all considered time intervals and rolling windows. Overall,this study sheds light on the effectiveness of the CSIE model in capturing market dynamics and highlights its potential utility in enhancing risk management strategies within stock markets.