Suchergebnisse

This paper presents a new multivariate GARCH model with time-varying conditional correlation structure which is a generalization of the Regime Switching Dynamic Correlation (RSDC) of Pelletier (2006). This model, which we name Hierarchical RSDC, is building with the hierarchical generalization of the hidden Markov model introduced by Fine et al. (1998). This can be viewed graphically as a tree-structure with different types of states. The first are called production states and they can emit observations, as in the classical Markov-Switching approach. The second are called abstract states. They can't emit observations but establish vertical and horizontal probabilities that define the dynamic of the hidden hierarchical structure. The main gain of this approach compared to the classical Markov-Switching model is to increase the granularity of the regimes. Our model is also compared to the new Double Smooth Transition Conditional Correlation GARCH model (DSTCC), a STAR approach for dynamic correlations proposed by Silvennoinen and Teräsvirta (2007). The reason is that under certain assumptions, the DSTCC and our model represent two classical competing approaches to modeling regime switching. We also perform Monte-Carlo simulations and we apply the model to two empirical applications studying the conditional correlations of selected stock returns. Results show that the Hierarchical RSDC provides a good measure of the correlations and also has an interesting explanatory power.

Recent increases in energy prices, especially oil prices, have become a principal concern for consumers, corporations, and governments. Most analysts believe that oil price fluctuations have considerable consequences on economic activity. Oil markets have become relatively free, resulting in a high degree of oil-price volatility and generating radical changes to world energy and oil industries. As a result oil markets are naturally vulnerable to significant negative volatility. An example of such a case is the oil embargo crisis of 1973. In this newly created climate, protection against market risk has become a necessity. Value at Risk (VaR) measures risk exposure at a given probability level and is very important for risk management. Appealing aspects of Extreme Value Theory (EVT) have made convincing arguments for its use in managing energy price risks. In this paper, we apply both unconditional and conditional EVT models to forecast Value at Risk. These models are compared to the performances of other well-known modelling techniques, such as GARCH, historical simulation and Filtered Historical Simulation. Both conditional EVT and Filtered Historical Simulation procedures offer a major improvement over the parametric methods. Furthermore, GARCH(1, 1)-t model may provide equally good results, as well as the combining of the two procedures.

Recent increases in energy prices, especially oil prices, have become a principal concern for consumers, corporations, and governments. Most analysts believe that oil price fluctuations have considerable consequences on economic activity. Oil markets have become relatively free, resulting in a high degree of oil-price volatility and generating radical changes to world energy and oil industries. As a result oil markets are naturally vulnerable to significant negative volatility. An example of such a case is the oil embargo crisis of 1973. In this newly created climate, protection against market risk has become a necessity. Value at Risk (VaR) measures risk exposure at a given probability level and is very important for risk management. Appealing aspects of Extreme Value Theory (EVT) have made convincing arguments for its use in managing energy price risks. In this paper, we apply both unconditional and conditional EVT models to forecast Value at Risk. These models are compared to the performances of other well-known modelling techniques, such as GARCH, historical simulation and Filtered Historical Simulation. Both conditional EVT and Filtered Historical Simulation procedures offer a major improvement over the parametric methods. Furthermore, GARCH(1, 1)-t model may provide equally good results, as well as the combining of the two procedures.

Presents the main statistical tools of econometrics, focusing specifically on modern econometric methodology. The authors unify the approach by using a small number of estimation techniques, mainly generalized method of moments (GMM) estimation and kernel smoothing. The choice of GMM is explained by its relevance in structural econometrics and its preeminent position in econometrics overall. Split into four parts, Part I explains general methods. Part II studies statistical models that are best suited for microeconomic data. Part III deals with dynamic models that are designed for macroeconomic and financial applications. In Part IV the authors synthesize a set of problems that are specific to statistical methods in structural econometrics, namely identification and over-identification, simultaneity, and unobservability. Many theoretical examples illustrate the discussion and can be treated as application exercises. Nobel Laureate James A. Heckman offers a foreword to the work