Conditional Correlation Model Research Articles

Investigating the price volatility transmission mechanisms of selected fresh vegetable chains in Greece

PurposeThis paper attempts to model the transmission of volatility between producer and consumer prices in the fresh potato, tomato, and cucumber markets in Greece.Design/methodology/approachThe transmission mechanism of the price volatility is modeled using the most popular multivariate GARCH models while taking into consideration possible asymmetries in the transmission process. The models utilized are the DVECH and the BEKK models from the VECH family, as well as the CCC model and the DCC model from the family of conditional correlation models. The possible asymmetric effects are evaluated using asymmetric GARCH models, as well as estimating volatility impulse responses for independent shocks.FindingsThe results reveal that, in the tomato and cucumber markets, which are regulated by the Common Market Organization of fruits and vegetables, producers are less vulnerable to volatility shocks transmitted from consumers. In contrast, in the non-regulated potato market, producers are affected by spillover effects from consumers.Research limitations/implicationsThis study is limited to a few commodities (i.e. potatoes, tomatoes, and cucumbers); however, it could be extended to additional commodities.Practical implicationsThe results of this study show that, if producers are organized on a cooperative basis within the regulative framework of the CAP, like the tomato and cucumber producers, their place in the food supply chain is strengthened, although the CAP targets more market-oriented agricultural markets that are more exposed to world prices.Originality/valueThe present study attempts to understand the transmission of volatility between producer and consumer prices in the fresh potato, tomato, and cucumber markets in Greece, which is not apparent from previous studies. Furthermore, the volatility clusters that are identified in the present study are associated with certain CAP reforms.

A Score-Driven Conditional Correlation Model for Noisy and Asynchronous Data: An Application to High-Frequency Covariance Dynamics

The analysis of the intraday dynamics of covariances among high-frequency returns is challenging due to asynchronous trading and market microstructure noise. Both effects lead to significant data reduction and may severely affect the estimation of the covariances if traditional methods for low-frequency data are employed. We propose to model intraday log-prices through a multivariate local-level model with score-driven covariance matrices and to treat asynchronicity as a missing value problem. The main advantages of this approach are: (i) all available data are used when filtering the covariances, (ii) market microstructure noise is taken into account, (iii) estimation is performed by standard maximum likelihood. Our empirical analysis, performed on 1-sec NYSE data, shows that opening hours are dominated by idiosyncratic risk and that a market factor progressively emerges in the second part of the day. The method can be used as a nowcasting tool for high-frequency data, allowing to study the real-time response of covariances to macro-news announcements and to build intraday portfolios with very short optimization horizons.

Forecasting the Covolatility of Coffee Arabica and Crude Oil Prices: A Multivariate GARCH Approach with High-Frequency Data

Forecasting the covolatility of asset return series is becoming the subject of extensive research among academics, practitioners, and portfolio managers. This paper estimates a variety of multivariate GARCH models using weekly closing price (in USD/barrel) of Brent crude oil and weekly closing prices (in USD/pound) of Coffee Arabica and compares the forecasting performance of these models based on high-frequency intraday data which allows for a more precise realized volatility measurement. The study used weekly price data to explicitly model covolatility and employed high-frequency intraday data to assess model forecasting performance. The analysis points to the conclusion that the varying conditional correlation (VCC) model with Student’s t distributed innovation terms is the most accurate volatility forecasting model in the context of our empirical setting. We recommend and encourage future researchers studying the forecasting performance of MGARCH models to pay particular attention to the measurement of realized volatility and employ high-frequency data whenever feasible.

Portfolio Selection Under Systemic Risk

This paper proposes a novel methodology to construct optimal portfolios that explicitly incorporates the occurrence of systemic events. Investors maximize a modified Sharpe ratio that is conditional on a systemic event, with the latter interpreted as a low market return environment. We solve the portfolio allocation problem analytically under the absence of short-selling restrictions and numerically when short-selling restrictions are imposed. This approach for obtaining an optimal portfolio allocation is made operational by embedding it in a multivariate dynamic setting using dynamic conditional correlation and copula models. We evaluate the out-of-sample performance of our portfolio empirically on the US stock market over the period 2007 to 2020 using ex-post wealth paths and systemic risk metrics against mean-variance, equally-weighted, and global minimum variance portfolios. Our portfolio maximizing a modified Sharpe ratio outperforms all competitors under market distress and remains competitive in non-crisis periods.

In Search of Gold: Insights From Google Searches on Portfolio Hedging Effectiveness

Online investor attention, measured by Google searches, may provide valuable information for the assessment of the co-movement between financial assets. In our empirical analysis, we draw upon an extension of the dynamic conditional correlation model and find that online investor attention is a statistically significant determinant of the time-varying correlations between stocks and gold-, silver-, and crude oil future contracts. Our results, relying on daily data over eleven years, suggest that market participants may enrich asset allocation strategies by means of online investor attention. Taking a practical point of view, we demonstrate that the informational content of Google searches increases the hedging effectiveness of combined portfolios.

Analytical Gradients of Dynamic Conditional Correlation Models

We provide the analytical gradient of the full model likelihood for the Dynamic Conditional Correlation (DCC) specification by Engle (2002), the generalised version by Cappiello et al. (2006), and of the cDCC model by Aielli(2013). We discuss how the gradient might be further extended by introducing elements related to the conditional variance parameters, and discuss the issue arising from the estimation of constrained and/or reparametrised versions of the model. A computational simulation compares analytical versus numerical gradients, with a view to parameter estimation; we find that analytical differentiation yields more efficiency and improved accuracy.

Analytical Gradients of Dynamic Conditional Correlation models

In this note we provide the analytical gradient of the full model likelihood of the DCC specification of Engle (2002), the generalized version of Cappiello et al. (2006), and of the cDCC model of Aielli (2008).

FLIGHT-TO-QUALITY OR CONTAGION DURING U.S. SUBPRIME CRISIS: EVIDENCE FROM VIETNAM’S FINANCIAL MARKETS

Abstract: This study investigates whether contagion or flight-to-quality occurred in Vietnam’s financial markets during the US subprime crisis in 2007. We apply the asymmetric dynamic conditional correlation model (ADCC-GARCH (1,1)) to daily stock-index and bond index returns of Vietnam’s and US stock markets. We test for contagion or flight-to-quality by using a test for difference in dynamic conditional correlation means. The results show a contagion between the US and Vietnam’s stock markets, confirming the widespread influence of the US stock market on a young market like Vietnam. This result suggests a low benefit from diversification for investors holding portfolios containing assets in Vietnam’s stock market and US stock market during the crisis. Moreover, the relationship between Vietnam’s stock and bond markets represents a flight-to-quality during the US subprime crisis. This finding shows that the investors tend to hold less risky assets, i.e., bonds, instead of stocks during this turbulent period in Vietnam.Keywords: international financial contagion, flight-to-quality, Vietnam, US subprime crisis, ADCC-GARCH

Modified models and simulations for estimating dynamic functional connectivity in resting state functional magnetic resonance imaging.

As understanding the nature of brain networks through dynamic functional connectivity (dFC) estimation is of paramount significant, the introduction and revision of blood-oxygen-level dependent (BOLD) signal simulation methods in brain regions and dFC estimation methods have gained significant ground in recent years. Based on the observation of BOLD signals with multivariate nonnormal distribution in functional magnetic resonance imaging (fMRI) images, we first propose a copula-based method for the production of these signals, in which nonnormal data are generated with a selected time-varying covariance matrix. Therefore, we can compare the performance of models in the cases where brain signals have a multivariate nonnormal distribution. Then, two kendallized exponentially weighted moving average (KEWMA) and kendallized dynamic conditional correlation (KDCC) multivariate volatility models are introduced which are based on two well-known and commonly used exponentially weighted moving average (EMWA) and dynamic conditional correlation (DCC) models. The results show that KDCC model can estimate conditional correlation significantly far better than the former ones (ie, DCC, standardized dynamic conditional correlation, EWMA, and standardized exponentially weighted moving average) on both types of data (ie, multivariate normal and nonnormal). In the next step, the bivariate normal distribution in Iranian resting state fMRI data is confirmed by using statistical tests, and it is shown that the dynamic nature of FC is not optimally detected using prevalent methods. Two alternative Portmanteau and rank-based tests are proposed for the examination of conditional heteroscedasticity in data. Finally, dFC in these data is estimated by employing the KDCC model.

Dynamic conditional angular correlation

We introduce the concept of angular correlation for estimating the instantaneous correlation matrix with a single multivariate realization. The proposed estimator is generally a positive definite correlation matrix and robust in that for bivariate normal data, the sample angular correlation is equally likely to be above or below the population correlation coefficient. We then generalize the dynamic conditional correlation (DCC) model to the dynamic conditional angular correlation (DCAC) model. We demonstrate the efficacy and robustness of the proposed methods against leptokurticity, with some numerical experiments. In particular, a real application illustrates the better performance of the DCAC model than the DCC model in portfolio construction.

Multiplicative Conditional Correlation Models for Realized Covariance Matrices

We introduce a class of multiplicative dynamic models for realized covariance matrices assumed to be conditionally Wishart distributed. The multiplicative structure enables consistent three-step estimation of the parameters, starting by covariance targeting of a scale matrix. The dynamics of conditional variances and correlations are inspired by specifications akin to the consistent dynamic conditional correlation model of the multivariate GARCH literature, and estimation is performed by quasi maximum likelihood. Simulations show that in finite samples the three-step estimator has smaller bias and root mean squared error than the full estimator when the cross-sectional dimension increases. An empirical application illustrates the flexibility of these models in a low-dimensional setting, and another one illustrates their effectiveness and practical usefulness in high dimensional portfolio allocation strategies.

Projected Dynamic Conditional Correlations

We propose a novel specification of the Dynamic Conditional Correlation (DCC) model based on an alternative normalization of the pseudo-correlation matrix called Projected DCC (Pro-DCC). Our modification consists in projecting, rather than re-scaling, the pseudo-correlation matrix onto the set of correlation matrices in order to obtain a well defined conditional correlation matrix. A simulation study shows that projecting performs better than re-scaling when the dimensionality of the correlation matrix is large. An empirical application to the constituents of the S&P 100 shows that the proposed methodology performs favorably to the standard DCC in an out-of-sample asset allocation exercise.

The linkage between stock and inter-bank bond markets in China: A Dynamic Conditional Correlation (DCC) analysis

This study applies the Dynamic Conditional Correlation (DCC) model to investigate the correlation between stock and inter-bank bond markets in China over the period from 2002 to 2016. The study finds no conditional correlation between China's stock and bond markets over the sample period. However, after dividing the sample into four different time scales, we find a significant correlation for the following periods: bond market fluctuations (2002-2005), recovery and persistence (2010-2013), and stock market shock (2014-2016). However, there is an insignificant correlation during the Global Financial Crisis (2006-2009). Further, we apply the BEKK model as a confirmatory analysis and find the presence of spillover effects between the stock and bond markets in both directions during the following periods: bond market fluctuations, recovery and persistence, and stock market shock. These results suggest that the correlation between the stock and bond markets in China is a time dependent.

Weekly Dynamic Conditional Correlations Among Cryptocurrencies and Traditional Assets

This paper adopts a versatile multivariate conditional correlation model to estimate daily seasonality in the returns, the volatility, and the correlations between stocks, bonds, gold and Bitcoin. Besides the well known seasonality in stocks and bonds, the day-of-the-week effect is also present in Bitcoin. Mondays are associated with higher Bitcoin returns, while Wednesdays with higher Bitcoin volatility. As opposed to previous literature, our results indicate strong evidence of Bitcoin’s leverage effect. Moreover, we show that daily correlations between Bitcoin and traditional assets are higher at the beginning of the week, while the volatility of these correlations decreases over the week. Our results offer interesting insights in terms of investment and portfolio diversification, that can be applied to the analysis of systematic risk asset allocation and hedging.

Improved Large Dynamic Covariance Matrix Estimation With Graphical Lasso and Its Application in Portfolio Selection

The estimation of the large and high-dimensional covariance matrix and precision matrix is a fundamental problem in modern multivariate analysis. It has been widely applied in economics, finance, biology, social networks and health sciences. However, the traditional sample estimators perform poorly for large and high-dimensional data. There are many approaches to improve the covariance matrix estimation. The large dynamic conditional correlation model based on the nonlinear shrinkage and its application in portfolio selection attract increasing attention. In the estimation of the unconditional covariance matrix, the graphical lasso is more robust than the nonlinear shrinkage model, and the leptokurtic and fat tail characteristics of the asset returns are also more obvious. This article proposes improved large dynamic covariance matrix estimation based on the graphical lasso models under the multivariate normal distribution (glasso) and t distribution (tlasso), and the corresponding dynamic conditional correlation glasso and tlasso approaches are developed. To verify the effectiveness and robustness of the proposed methods, we conduct simulations and then apply the models to the classic Markowitz portfolio selection problem. Simulations and empirical results show that the combined dynamic conditional correlation glasso and tlasso approaches outperform the current dynamic covariance matrix estimators.

Nonlinearities and regimes in conditional correlations with different dynamics

New parameterizations of the dynamic conditional correlation (DCC) model and of the regime-switching dynamic correlation (RSDC) model are introduced, such that these models provide a specific dynamics for each correlation. They imply a nonlinear autoregressive form of dependence on lagged correlations and are based on properties of the Hadamard exponential matrix. The new models are applied to a data set of twenty stock market indices and a data set of the thirty Dow Jones components, comparing them to the classical DCC and RSDC models. The empirical results show that the new models improve their classical versions in terms of several criteria.

Volatility and dynamic currency hedging

We propose a dynamic and efficient global currency portfolio that can significantly decrease the risk of an exogenous portfolio of world equities. We demonstrate that our dynamic conditional correlation model, which is an application of Engle (2002), can decrease the estimated return variance of a portfolio of global equities by about 20 percent relative to the static model of Campbell et al. (2010). The Euro, the US Dollar, the Swiss Franc, and the Japanese Yen all move in a manner opposite to the world equity market, implying that they are safe-haven currencies. However, since the US financial crisis, the importance of the Japanese Yen in a global currency portfolio has grown, whereas that of the Euro has diminished. Increases in foreign-exchange-market volatility and US stock-market volatility have increased the importance of safe-haven currencies in optimal currency portfolios, and the impact of foreign-exchange-market volatility is more significant than that of US stock-market volatility. We also find a spillover effect from both US stock-market and US foreign-exchange-market volatilities to the foreign-exchange-market volatility of other currencies.

The contagion of the Greek debt crisis on the EMU sovereign bond markets: a Garch-DCC approach

We use the dynamic conditional correlation (DCC) model of Engle (2002) to examine the contagion effects from the Greek debt crisis on seven Economic and Monetary Union (EMU) sovereign bond markets. Following this purpose, daily data on ten-year sovereign bond yields for each market were collected for a period ranging from 1 September 2009 to 31 December 2015. We show a strong evidence of contagion effects from the Greek sovereign bond market to those of the other peripheral countries during the spring of 2010 suggesting a «wake-up call contagion» phenomenon. Except for this period, the DCC return series strongly reject the hypothesis of contagion stemming from the ten-year Greek government bond to our seven sovereign debt markets. We thus argue that over time, investors became more confident that the Greek debt crisis was a special case independent from the other countries. Our results are very important for policymakers and investors.

Spillover Effects Between Stock Prices and Exchange Rates for the Central and Eastern European Countries

This article attempts to empirically analyze the dynamic relationship and volatility spillover effects between exchange rates and stock returns of the five Central and Eastern European (CEE) countries (Hungary, Poland, the Czech Republic, Romania and Croatia) covering the period 2000–2017 by using the bivariate generalized autoregressive conditional heteroskedasticity-Baba, Engle, Kraft and Kroner (GARCH-BEKK) framework alongside with the constant and dynamic conditional correlation (CCC and DCC) models. The major findings reveal the following: bidirectional volatility spillovers between the two financial markets in Hungary, the Czech Republic and Croatia in the pre-crisis period; unidirectional spillover of volatility from the stock market to foreign exchange market for Poland during the sub-prime crisis period; unidirectional spillover of volatility from the foreign exchange market to the stock market for Hungary in the post-crisis period and Romania in the pre-crisis period; non-persistence volatility spillover between them in case of the Czech Republic, Romania and Croatia in the post-crisis period; the absence of volatility transmission from the stock market to foreign exchange market occurs in Hungary, while from the foreign exchange market to the stock market in case of Poland in the post-crisis period. We further find a short-lived but non-negligible financial contagion between stock and foreign exchange market in these countries. These empirical insights have significant implications for portfolio investments and currency risk hedging.

Dynamic conditional correlation and volatility distributions in Tokyo, London, and New York gold markets

This study investigates the volatility and co-movement of gold prices across Tokyo, London, and New York gold markets. Using a dynamic conditional correlation (DCC) model, the authors estimate the cross-correlation and volatility of gold in each pair among three markets over the period from 1993 to 2012. Both the time-varying correlations and realized distributions are explored. After estimating the DCC as well as the corresponding distributions of the DCC among the three markets, the results suggest that: (i) the DCC probability distribution of London and New York shows a higher volatility associated with a higher DCC value; (ii) the DCC probability distribution between London and New York as well as between Tokyo and London both express the similar and overlapping pattern, implying that these markets are almost equal, and neither dominates; and (iii) New York exhibits a spillover effect of Tokyo’s variance, while the latter does not influence New York’s variance. The shapes of the distributions show that the distribution of high DCC is wider than that of low DCC, meaning that risk increases with the dynamic correlation. The implications of these gold DCC probability distributions encourage investors to diversify their global portfolios and manage latent risks in different gold markets effectively. Besides, the volatility-threshold DCC model suggests that the correlations are more sensitive to extreme volatility thresholds in London and New York markets, whereas the correlation is significantly affected by all levels of volatility at 50%, 75%, 90%, and 95% thresholds in Tokyo and London markets. Investors may not be able to diversify portfolio risk by choosing London and New York at the same time once gold becomes volatile as a high correlation is observed in the extreme thresholds.