Modelling Returns and Volatilities During Financial Crises: a Time Varying Coefficient Approach

TL;DR

This paper investigates how financial crises impact the dynamics of returns and volatilities in stock markets, revealing increased time variation in volatility persistence and spillovers, using a novel time-varying coefficient modeling approach.

Contribution

It introduces a comprehensive time-varying coefficient model for financial time series, providing new solutions for low order specifications and insights into dynamic correlations and spillovers during crises.

Findings

Stock returns show increased volatility persistence during crises.

Time-varying correlations and spillovers are more prominent during financial crises.

The model enables multistep ahead predictions and characterizes covariance structures.

Abstract

We examine how the most prevalent stochastic properties of key financial time series have been affected during the recent financial crises. In particular we focus on changes associated with the remarkable economic events of the last two decades in the mean and volatility dynamics, including the underlying volatility persistence and volatility spillovers structure. Using daily data from several key stock market indices we find that stock market returns exhibit time varying persistence in their corresponding conditional variances. Furthermore, the results of our bivariate GARCH models show the existence of time varying correlations as well as time varying shock and volatility spillovers between the returns of FTSE and DAX, and those of NIKKEI and Hang Seng, which became more prominent during the recent financial crisis. Our theoretical considerations on the time varying model which provides the platform upon which we integrate our multifaceted empirical approaches are also of independent interest. In particular, we provide the general solution for low order time varying specifications, which is a long standing research topic. This enables us to characterize these models by deriving, first, their multistep ahead predictors, second, the first two time varying unconditional moments, and third, their covariance structure.