Power-law correlations in finance-related Google searches, and their cross-correlations with volatility and traded volume: Evidence from the Dow Jones Industrial components
arXiv:1502.00225 · doi:10.1016/j.physa.2015.02.057
Abstract
We study power-law correlations properties of the Google search queries for Dow Jones Industrial Average (DJIA) component stocks. Examining the daily data of the searched terms with a combination of the rescaled range and rescaled variance tests together with the detrended fluctuation analysis, we show that the searches are in fact power-law correlated with Hurst exponents between 0.8 and 1.1. The general interest in the DJIA stocks is thus strongly persistent. We further reinvestigate the cross-correlation structure between the searches, traded volume and volatility of the component stocks using the detrended cross-correlation and detrending moving-average cross-correlation coefficients. Contrary to the universal power-law correlations structure of the related Google searches, the results suggest that there is no universal relationship between the online search queries and the analyzed financial measures. Even though we confirm positive correlation for a majority of pairs, there are several pairs with insignificant or even negative correlations. In addition, the correlations vary quite strongly across scales.
arXiv comment22 pages, 6 figures
References in corpus (13)
- Multifractal detrended fluctuation analysis of nonstationary time series
- Detrended Cross-Correlation Analysis: A New Method for Analyzing Two Non-stationary Time Series
- Effect of Trends on Detrended Fluctuation Analysis
- Multifractal detrended cross-correlation analysis for two nonstationary signals
- Multifractal detrending moving average cross-correlation analysis
- The Twitter of Babel: Mapping World Languages through Microblogging Platforms
- On Hurst exponent estimation under heavy-tailed distributions
- Scaling laws of human interaction activity
- Web search queries can predict stock market volumes
- Measuring correlations between non-stationary series with DCCA coefficient
- Detrending moving-average cross-correlation coefficient: Measuring cross-correlations between non-stationary series
- Can Google Trends search queries contribute to risk diversification?
- Entangling mobility and interactions in social media