Dynamic Conditional Correlation GARCH Model Research Articles

Volatility spillovers across daytime and overnight information between China and world equity markets

This article explores the transmission of daytime and overnight information in terms of returns and volatility between Chinese and Asian, European and North American main stock markets. We propose a bivariate analysis with China as benchmark. By testing the constancy of the conditional correlations, we use an extended constant or dynamic conditional correlation GARCH model. The empirical findings show that across the daytime information transmissions, the relationships between China and Asian markets are closer than China and non-Asian markets, whereas through the overnight information transmissions these relationships are inverse. The analysis provides, before the crisis, that the overnight volatility spillover effects are from China to the United States and the United Kingdom. During the crisis, China affects the United Kingdom in terms of daytime volatility spillovers, whereas in terms of overnight volatility spillovers China affects the United States and is influenced by Japan. After the crisis, daytime volatility spillovers are from Taiwan to China, whereas the overnight volatility spillover effects are from China to the United States and the United Kingdom.

A Wavelet-based MRA-EDCC-GARCH Methodology for the Detection of News and Volatility Spillover across Sectoral Indices—Evidence from the Indian Financial Market

The article studies the nature and direction of shock and volatility transmission among the nine non-overlapping sectoral indices of Bombay Stock Exchange (BSE) across eight different scales (from 2–4 days to 1–2 years) using a newly developed wavelet-based multi-resolution–extended dynamic conditional correlation GARCH (MRA–EDCC GARCH) model and compared the results with that of the traditional vector-auto regression–extended dynamic conditional correlation GARCH (VAR–EDCC GARCH) model. The study reveals that the volatility interaction is scale dependent. Significant variation in the magnitude and direction of the spillover incidences are observed between the results of the two models which elucidates that the traditional VAR–EDCC GARCH model may not be sufficient in unlocking the complex pattern of volatility interaction and the multiscale analysis can be further used to extract the hidden information. Shock spillover incidences are found to decrease with scale while the volatility spillover is found to vary both in magnitude and direction across scales. Previous literatures have established that volatility interaction among financial assets can be leveraged successfully in designing trading strategies that generates better results in comparison to the trading strategies that does not employ volatility interactions in their model. Given the findings that the magnitude and direction of volatility interaction changes with the change in investment horizon, it can be concluded that a strategy calibrated for short-term traders may not be optimal for long-term traders and vice versa.

On the Stationarity of Dynamic Conditional Correlation Models

We provide conditions for the existence and the unicity of strictly stationary solutions of the usual Dynamic Conditional Correlation GARCH models (DCC-GARCH). The proof is based on Tweedie's (1988) criteria, after having rewritten DCC-GARCH models as nonlinear Markov chains. Moreover, we study the existence of their finite moments.

Dynamic correlation analysis of spill-over effects of interest rate risk and return on Australian and US financial firms

This paper examines the spill-over effects of interest rate risk and return on Australian and US financial firms using a dynamic conditional correlation GARCH model. Australian banks exhibit negative exposure to changes in both domestic and US interest rates, and US interest rate volatility is found to be an important predictor of Australian bank stock return volatility. Similar findings are obtained for the aggregate portfolio of financial stocks. The time-varying conditional correlation between Australian and US financial stock returns increases during financial crises and varies directly with net capital flows between Australia and the US. Further, the conditional correlation increases (decreases) during the contractionary (expansionary) periods of the US business cycle.

Co-movements among major European exchange rates: A multivariate time-varying asymmetric approach

This paper adopts a multivariate asymmetric dynamic conditional correlation GARCH model to examine the interdependence of US dollar (USD) exchange rates expressed in euro (EUR), British pound (GBP), and Swiss franc (CHF). The effect of Europe's recent financial turmoil on these dynamic correlations is investigated. The findings suggest asymmetric responses in correlations among the three exchange rates, namely, higher dependency during periods of joint appreciation than during periods of joint depreciation. Moreover, the results indicate that the crisis may have triggered the shift of fund flows to CHF in particular, which is widely believed to be a safe-haven currency.

Efficient Generation Portfolio Construction Using Time-Varying Correlations

We constructed a procurement portfolio for the Indian power sector using two variants of the dynamic conditional correlation GARCH model to derive time-varying correlations between major coal indices. We used prices and qualities of observed cargos to adjust indices for quality gaps as well as for freight costs and power plant efficiency factors. Using the relative homogeneity of the energy content of imports from Australia, South Africa, and Indonesia, we found that the regional seaborne market is highly correlated during normal economic conditions, while suffering brief departures in correlation during demand and supply shocks. Our results show that the buying behavior of power producers is aligned with the mean-variance efficient portfolio of delivered prices using time-varying correlation estimates, but not free-on-board coal index prices. This study challenges the notion that thermal coal importers only source material with a freight price advantage and highlights the importance of coal quality gaps in power production.

Dynamic stock market covariances in the Eurozone

This paper examines the short-term dynamics, macroeconomic sensitivities, and longer-term trends in the variances and covariances of national equity market index daily returns for eleven countries in the Euro currency zone. We modify Colacito, Engle and Ghysel's Mixed Data Sampling Dynamic Conditional Correlation Garch model to include a new scalar measure for the degree of correlatedness in time-varying correlation matrices. We also explore the robustness of the findings with a less model-dependent realized covariance estimator. We find a secular trend toward higher correlation during our sample period, and significant linkages between macroeconomic and market-wide variables and dynamic correlation. One notable finding is that average correlation between these markets is lower when their average GDP growth rate is lower or when more of them have negative GDP growth.

Robust forecasting of dynamic conditional correlation GARCH models

Large one-off events cause large changes in prices, but may not affect the volatility and correlation dynamics as much as smaller events. In such cases, standard volatility models may deliver biased covariance forecasts. We propose a multivariate volatility forecasting model that is accurate in the presence of large one-off events. The model is an extension of the dynamic conditional correlation (DCC) model. In our empirical application to forecasting the covariance matrix of the daily EUR/USD and Yen/USD return series, we find that our method produces more precise out-of-sample covariance forecasts than the DCC model. Furthermore, when used in portfolio allocation, it leads to portfolios with similar return characteristics but lower turnovers, and hence higher profits.

An economic evaluation of stock–bond return comovements with copula-based GARCH models

Owing to their importance in asset allocation strategies, the comovements between the stock and bond markets have become an increasingly popular issue in financial economics. Moreover, the copula theory can be utilized to construct a flexible joint distribution that allows for skewness in the distribution of asset returns as well as asymmetry in the dependence structure between asset returns. Therefore, this paper proposes three classes of copula-based GARCH models to describe the time-varying dependence structure of stock–bond returns, and then examines the economic value of copula-based GARCH models in the asset allocation strategy. We compare their out-of-sample performance with other models, including the passive, the constant conditional correlation (CCC) GARCH and the dynamic conditional correlation (DCC) GARCH models. From the empirical results, we find that a dynamic strategy based on the GJR-GARCH model with Student-t copula yields larger economic gains than passive and other dynamic strategies. Moreover, a less risk-averse investor will pay higher performance fees to switch from a passive strategy to a dynamic strategy based on copula-based GARCH models.

Dynamic Stock Market Covariances in the Eurozone

This paper examines the short-term dynamics, macroeconomic sensitivities, and longer-term trends in the variances and covariances of national equity market index daily returns for eleven countries in the Euro currency zone. We modify Colacito, Engle and Ghysel's Mixed Data Sampling Dynamic Conditional Correlation Garch model to include a new scalar measure for the degree of correlatedness in time-varying correlation matrices. We also explore the robustness of the findings with a less model-dependent realized covariance estimator. We find a secular trend toward higher correlation during our sample period, and significant linkages between macroeconomic and market-wide variables and dynamic correlation. One notable finding is that average correlation between these markets is lower when their average GDP growth rate is lower or when more of them have negative GDP growth.

Dynamic Correlation Analysis of Asian Stock Markets

This paper examines the stock market linkages within the Asia-Pacific region and between Asian markets and the U.S. market over the period of January 2000 to June 2010, employing the dynamic conditional correlation GARCH model. Our results show that there exist very high correlations among the stock markets during the 2008 financial crisis. Therefore, consistent with the finding in literature, there are no diversification benefits during the financial crisis. However, our results show that there are still substantial opportunities for global investors to improve the risk-return performance between China and other markets during the sample period. In addition, we find evidence that the U.S. market significantly affects the stock markets in the Asia-Pacific region. Using T-GARCH model, there is a strong evidence of an asymmetric effect on conditional variance except stock markets in China and Malaysia.

The Stock-Bond Comovements in the Paris Bourse: Historical Evidence

Using some recently developed Paris Bourse 19th century price indexes; we study the stock-bond monthly return comovement for a 76 years long period. The comovements of stocks not only with government bonds, like majority of studies on this subject, but also with corporate bonds have been considered in this paper. A multivariate Dynamic conditional correlation GARCH(DCC GARCH) model has been implemented to assess the stock-bond return time varying correlation. The model succeeds to capture well enough the behavior of stocks and bonds returns. We do obtain variable but always highly positive conditional stock-bond correlations. The Granger causality tests which we have conducted per sub periods shows as we approach to the end of the 19th century the corporate bond market becomes more and more dominant in term of price adjustment and therefore more efficient.

Value at Risk의 사후검증을 통한 다변량 시계열자료의 차원축소 방법의 비교: 사례분석

금융자산에의 투자에서 리스크 관리의 중요성이 부각되면서 리스크를 측정할 수 있는 도구로서 Value at Risk (VaR)가 널리 각광을 받고 있다. Value at Risk는 주어진 신뢰수준에서 목표기간 동안 발생 가능한 최대손실로 정의되는데 몇 가지 한계점이 있지만 비교적 간단하게 계산되고 이해될 수 있다는 장점이 있어 리스크 측정 및 관리의 기본적인 측도로 이용되고 있다. 그러나 포트폴리오에 포함되는 자산의 숫자가 많아지는 경우 VaR을 계산하는 데에 필수적인 변동성 추정이 매우 어려워지게 된다. 이때 차원축소의 방법을 생각할 수 있는데, 전통적인 인자분석은 시계열자료에 적합한 방법이 아니기 때문에 직접 적용할 수 없고 자료의 자기상관성을 제거하는 방법이 선행되어야 한다. 본 논문에서는 인자분석의 확장 형태인 시계열인자분석을 활용하여 시계열자료의 차원축소과정을 간결하게 하는 방법을 제시하고, 시계열인자분석으로 차원을 축소할 때 기존의 방법을 사용하는 것과 어떠한 차이가 있는지를 실제 금융자료를 이용한 VaR의 사후검증을 통해 분석하였다. Value at Risk(VaR) is being widely used as a simple tool for measuring financial risk. Although VaR has a few weak points, it is used as a basic risk measure due to its simplicity and easiness of understanding. However, it becomes very difficult to estimate the volatility of the portfolio (essential to compute its VaR) when the number of assets in the portfolio is large. In this case, we can consider the application of a dimension reduction technique; however, the ordinary factor analysis cannot be applied directly to financial data due to autocorrelation. In this paper, we suggest a dimension reduction method that uses the time-series factor analysis and DCC(Dynamic Conditional Correlation) GARCH model. We also compare the method using time-series factor analysis with the existing method using ordinary factor analysis by backtesting the VaR of real data from the Korean stock market.

The Stock-Bond Comovements in the Paris Bourse: Historical Evidence

This paper aims to advance empirical knowledge of stock-bonds comovements thanks to the specific context of the pre-1914 French market. This period allows the measurement of the conditional correlation without any inflation thanks to the Gold standard regime. A multivariate Dynamic Conditional Correlation GARCH (DCC GARCH) model is implemented on four recently developed market indices to assess the varying correlation between stock and bond returns. We do obtain fluctuating but always highly positive conditional stock-bond correlations over a period of 76 years. This high correlation is observed not only with government bonds, as is the case in the majority of studies on this subject, but also with corporate bonds. Several macroeconomic factors are also tested to estimate their impact on the conditional correlations.

Robust Forecasting of Dynamic Conditional Correlation GARCH Models

Large once-off events cause large changes in prices but may not affect volatility and correlation dynamics as much as smaller events. Standard volatility models may deliver biased covariance forecasts in this case. We propose a multivariate volatility forecasting model that is accurate in the presence of large once-off events. The model is an extension of the dynamic conditional correlation model (DCC) model. Compared to the DCC model, our method produces more precise out-of-sample covariance forecasts and, when used in portfolio allocation, it leads to portfolios with similar return characteristics but lower turnover and hence higher profits.

Asymmetric Correlation and Volatility Dynamics among Stock, Bond, and Securitized Real Estate Markets

We apply a multivariate asymmetric generalized dynamic conditional correlation GARCH model to daily index returns of S&P500, US corporate bonds, and their real estate counterparts (REITs and CMBS) from 1999 to 2008. We document, for the first time, evidence for asymmetric volatilities and correlations in CMBS and REITs. Due to their high levels of leverage, REIT returns exhibit stronger asymmetric volatilities. Also, both REIT and stock returns show strong evidence of asymmetries in their conditional correlation, suggesting reduced hedging potential of REITs against the stock market downturn during the sample period. There is also evidence that corporate bonds and CMBS may provide diversification benefits for stocks and REITs. Furthermore, we demonstrate that default spread and stock market volatility play a significant role in driving dynamics of these conditional correlations and that there is a significant structural break in the correlations caused by the recent financial crisis.

Time-varying synchronization of European stock markets

We study intraday comovements among three developed (France, Germany, and the United Kingdom) and three emerging (the Czech Republic, Hungary, and Poland) European stock markets. When applying a Dynamic Conditional Correlation GARCH model to 5- min tick intraday stock price data (2003–2006), we find a strong correlation between the German and French markets and also between these two markets and the UK stock market. However, very little systematic positive correlation during a trading day can be detected between the developed and emerging stock markets, or within the emerging group itself. Hungary exhibits higher correlation with the developing markets and the emerging markets and its dynamics show an increasing trend; Poland and the Czech Republic produce less clear-cut results.

Robust Forecasting of Dynamic Conditional Correlation GARCH Models

Robust Forecasting of Dynamic Conditional Correlation GARCH Models

Time‐varying characteristics of cross‐market linkages with empirical application to Gulf stock markets

Purpose – The purpose of this paper is to propose an empirical procedure for examining the time‐varying features of cross‐market correlations in selected Gulf stock markets.Design/methodology/approach – The paper directly infers the cross‐market linkages from the stock data using a multivariate dynamic conditional correlation GARCH model (DCC‐GARCH). The paper attempts to date the structural breaks in the time‐paths of the conditional correlation indices to investigate whether the cross‐market comovement encompasses significant changes in nature or not.Findings – Conditional cross‐market correlations between studied markets are shown to be time‐varying, past‐dependent and subject to structural breaks. However, the comovements are still small within the Gulf region and insignificant between the Gulf stock markets and the world market.Research limitations/implications – Even though the paper attempted to relate the observed changes in market linkages to major economic and political events that the Gulf regi...

The estimation and determinants of emerging market country risk and the dynamic conditional correlation GARCH model

Country risk assessment is central to the international investment, which recently has increasingly focused on emerging markets (EM). In this paper we proxy for country risk in EM by using time-varying beta. We extend existing literature by applying a dynamic conditional correlation GARCH model. After confirming beta is time varying in twenty EM over the period January 1995 to December 2008 we investigate the GARCH (1,1) model and find the t-distribution generates the lowest forecast errors compared to the normal error distribution and a generalised error distribution. In a comparison of previous modelling techniques the results of our modified Diebold–Mariano test statistics suggest that the Kalman Filter model outperforms the GARCH model and the Schwert and Seguin (1990) model. Using a DCC-GARCH model our evidence suggests that considering dynamic betas can improve beta out-of-sample predicting ability and therefore offers potential gains for investors. Finally, we find dynamic betas across EM are strongly associated with each nation's interest rates, US interest rates and the Consumer Price Index (CPI) and to a lesser extent the exchange rates. Our results have some similarities to those in previous studies of developed markets in the economic determinants of time-varying beta but differences exist in the results on best model to forecast time-varying beta. These findings have implications for estimating country risk for investment and risk management purposes in EM.