Dynamic correlations at different time-scales with Empirical Mode Decomposition

TL;DR

This paper uses Empirical Mode Decomposition to analyze how correlations between financial indices vary across different time-scales and lags, revealing complex interaction patterns useful for financial decision-making.

Contribution

It introduces a novel application of EMD to study time-scale dependent correlations in financial indices, uncovering heterogeneity and lead-lag relationships.

Findings

Correlations vary significantly across time-scales and indices.

Identifies important lead-lag relationships at different time-scales.

Reveals heterogeneity in interactions useful for finance applications.

Abstract

The Empirical Mode Decomposition (EMD) provides a tool to characterize time series in terms of its implicit components oscillating at different time-scales. We apply this decomposition to intraday time series of the following three financial indices: the S\&P 500 (USA), the IPC (Mexico) and the VIX (volatility index USA), obtaining time-varying multidimensional cross-correlations at different time-scales. The correlations computed over a rolling window are compared across the three indices, across the components at different time-scales, at different lags and over time. We uncover a rich heterogeneity of interactions which depends on the time-scale and has important led-lag relations which can have practical use for portfolio management, risk estimation and investments.