Long-range Correlation and Market Segmentation in Bond Market

TL;DR

This paper investigates long-range auto- and cross-correlations in the bond market, revealing market segmentation and changes over time, using DMA and complex network methods to analyze empirical data.

Contribution

It introduces a novel complex network-based method to study long-range cross-correlations and applies it to bond market data, confirming market segmentation and temporal correlation dynamics.

Findings

Long-range auto-correlations peak at short-term maturities.

Market segmentation pattern identified in long-term correlations.

Long-range auto-correlations decrease while cross-correlations strengthen over recent years.

Abstract

This paper looks into the analysis of the long-range auto-correlations and cross-correlations in bond market. Based on Detrended Moving Average (DMA) method, empirical results present a clear evidence of long-range persistence that exists in one year scale. The degree of long-range correlation related to maturities has an upward tendency with a peak in short term. These findings confirm the expectations of fractal market hypothesis (FMH). Furthermore, we have developed a method based on a complex network to study the long-range cross-correlation structure and apply it to our data, and found a clear pattern of market segmentation in the long run. We also detected the nature of long-range correlation in the sub-period 2007 to 2012 and 2011 to 2016. The result from our research shows that long-range auto-correlations are decreasing in the recent years while long-range cross-correlations are strengthening.