Institute of Information Theory and Automation

You are here

Publication details

Wavelet-Based Correlation Analysis of the Key Traded Assets

Monography Chapter

Baruník Jozef, Kočenda Evžen, Vácha Lukáš

serial: Wavelet Applications in Economics and Finance, p. 157-183

project(s): GA13-24313S, GA ČR, GA14-24129S, GA ČR

keywords: time-frequency dynamics, high-frequency data, dynamic correlation

preview: Download

abstract (eng):

This chapter reveals the time-frequency dynamics of the dependence among key traded assets – gold, oil, and stocks, in the long run, over a period of 26 years. Using both intra-day and daily data and employing a variety of methodologies, including a novel time-frequency approach combining wavelet-based correlation analysis with high-frequency data, we provide interesting insights into the dynamic behavior of the studied assets. We account for structural breaks and reveal a radical change in correlations after 2007-2008 in terms of time-frequency behavior. Our results confirm different levels of dependence at various investment horizons indicating heterogeneity in stock market participants’ behavior, which has not been documented previously. While these key assets formerly had the potential to serve as items in a well-diversified portfolio, the events of 2007-2008 changed this situation dramatically.


bocek: 2012-12-21 16:10