|
|
Realized Jump GARCH model: Can decomposition of volatility improve its forecasting?
Poláček, Jiří ; Baruník, Jozef (advisor) ; Pertold-Gebicka, Barbara (referee)
The present thesis focuses on exploration of the applicability of realized measures in volatility modeling and forecasting. We provide a first comprehensive study of jump variation impact on future volatility of Central and Eastern European stock markets. As a main workhorse, the recently proposed Realized Jump GARCH model, which enables a study of the impact of jump variation on future volatility forecasts, is used. In addition, we estimate Realized GARCH and heterogeneous autoregressive (HAR) models using one-minute and five-minute high frequency data. We find that jumps are important for future volatility, but only to a limited extent due to the high level of information aggregation within the stock market index. Moreover, Realized (Jump) GARCH models outperform the standard GARCH model in terms of data fit and forecasting performance. Comparison of forecasts with HAR models reveals that Realized (Jump) GARCH models capture higher portion of volatility variation. Eventually, Realized Jump GARCH compared to other Realized GARCH models provides comparable or even better forecasting performance.
|
|
|
Realized Jump GARCH model: Can decomposition of volatility improve its forecasting?
Poláček, Jiří ; Baruník, Jozef (advisor) ; Pertold-Gebicka, Barbara (referee)
The present thesis focuses on exploration of the applicability of realized measures in volatility modeling and forecasting. We provide a first comprehensive study of jump variation impact on future volatility of Central and Eastern European stock markets. As a main workhorse, the recently proposed Realized Jump GARCH model, which enables a study of the impact of jump variation on future volatility forecasts, is used. In addition, we estimate Realized GARCH and heterogeneous autoregressive (HAR) models using one-minute and five-minute high frequency data. We find that jumps are important for future volatility, but only to a limited extent due to the high level of information aggregation within the stock market index. Moreover, Realized (Jump) GARCH models outperform the standard GARCH model in terms of data fit and forecasting performance. Comparison of forecasts with HAR models reveals that Realized (Jump) GARCH models capture higher portion of volatility variation. Eventually, Realized Jump GARCH compared to other Realized GARCH models provides comparable or even better forecasting performance.
|
|
|
Modeling Conditional Quantiles of Central European Stock Market Returns
Burdová, Diana ; Baruník, Jozef (advisor) ; Krištoufek, Ladislav (referee)
Most of the literature on Value at Risk concentrates on the unconditional nonparametric or parametric approach to VaR estimation and much less on the direct modeling of conditional quantiles. This thesis focuses on the direct conditional VaR modeling, using the flexible quantile regression and hence imposing no restrictions on the return distribution. We apply semiparamet- ric Conditional Autoregressive Value at Risk (CAViaR) models that allow time-variation of the conditional distribution of returns and also different time-variation for different quantiles on four stock price indices: Czech PX, Hungarian BUX, German DAX and U.S. S&P 500. The objective is to inves- tigate how the introduction of dynamics impacts VaR accuracy. The main contribution lies firstly in the primary application of this approach on Cen- tral European stock market and secondly in the fact that we investigate the impact on VaR accuracy during the pre-crisis period and also the period covering the global financial crisis. Our results show that CAViaR models perform very well in describing the evolution of the quantiles, both in abso- lute terms and relative to the benchmark parametric models. Not only do they provide generally a better fit, they are also able to produce accurate forecasts. CAViaR models may be therefore used as a...
|
|
|
Macroeconomic News and Their Impact on Sovereign Credit Risk Premia
Pištora, Vojtěch ; Hausenblas, Václav (advisor) ; Bobková, Božena (referee)
This thesis provides evidence of how macroeconomic surprises, constructed as deviations from market expectations, impact daily spread changes of Czech, Polish and Hungarian (CEEC-3) government bonds and sovereign credit default swaps. Firstly, we carried out series of event studies that inspect the spreads' reactions to the announcements. Subsequently, we employed the general-to-specific modeling approach and arrived at thirty GARCH-type models that consider surprises' impact on both conditional mean and variance. We have found significant impacts on the mean, yet in terms of magnitude, the impact of macroeconomic surprises has not been superior to that of broad financial factors. The impact on spreads' volatility appears more consequential though it lacks a clear pattern: Both good and bad news have been found to affect the volatility in either direction. Our findings suggest that with respect to macroeconomic news, daily changes of the bond spreads are driven rather by inflation expectations than by credit risk considerations. Foreign news proxied by the German surprises seems to affect the CEEC-3 bond spreads mainly through the risk-free proxy - the German Bund yield. Contrary to studies using low-frequency macroeconomic data, we have found no evidence for the "wake-up call" hypothesis.
|
|
|
Some modifications of models ARCH for financial time series
Nekvinda, Matěj ; Cipra, Tomáš (advisor) ; Zichová, Jitka (referee)
This work deals with modelling time series, especially their volatility, by methods based on the ARCH model. In the beginning, we describe the general features of financial time series, afterwards we focus on the ARCH model modifications. The described modifications are GARCH, EGARCH, GJR-GARCH and briefly GARCH-M, IGARCH, FIGARCH and QGARCH. Along with the models, there is a description of their behaviour, which frequently reflects some features of financial time series. We also mention the process of practical financial time series analysis. In the end, we demonstrate the application of GARCH, EGARCH and GJR-GARCH models for modelling values of FTSE 100 index together with diagnostic tests and prediction. Powered by TCPDF (www.tcpdf.org)
|
|
|
Modeling Conditional Quantiles of Central European Stock Market Returns
Burdová, Diana ; Baruník, Jozef (advisor) ; Krištoufek, Ladislav (referee)
Most of the literature on Value at Risk concentrates on the unconditional nonparametric or parametric approach to VaR estimation and much less on the direct modeling of conditional quantiles. This thesis focuses on the direct conditional VaR modeling, using the flexible quantile regression and hence imposing no restrictions on the return distribution. We apply semiparamet- ric Conditional Autoregressive Value at Risk (CAViaR) models that allow time-variation of the conditional distribution of returns and also different time-variation for different quantiles on four stock price indices: Czech PX, Hungarian BUX, German DAX and U.S. S&P 500. The objective is to inves- tigate how the introduction of dynamics impacts VaR accuracy. The main contribution lies firstly in the primary application of this approach on Cen- tral European stock market and secondly in the fact that we investigate the impact on VaR accuracy during the pre-crisis period and also the period covering the global financial crisis. Our results show that CAViaR models perform very well in describing the evolution of the quantiles, both in abso- lute terms and relative to the benchmark parametric models. Not only do they provide generally a better fit, they are also able to produce accurate forecasts. CAViaR models may be therefore used as a...
|
|
|
Value at Risk: GARCH vs. Stochatistic Volatility Models: Empirical Study
Tesárová, Viktória ; Gapko, Petr (advisor) ; Seidler, Jakub (referee)
The thesis compares GARCH volatility models and Stochastic Volatility (SV) models with Student's t distributed errors and its empirical forecasting per- formance of Value at Risk on five stock price indices: S&P, NASDAQ Com- posite, CAC, DAX and FTSE. It introduces in details the problem of SV models Maximum Likelihood examinations and suggests the newly devel- oped approach of Efficient Importance Sampling (EIS). EIS is a procedure that provides an accurate Monte Carlo evaluation of likelihood function which depends upon high-dimensional numerical integrals. Comparison analysis is divided into in-sample and out-of-sample forecast- ing performance and evaluated using standard statistical probability back- testig methods as conditional and unconditional coverage. Based on empirical analysis thesis shows that SV models can perform at least as good as GARCH models if not superior in forecasting volatility and parametric VaR. 1
|
|
|
Volume - volatility relation across different volatility estimators
Kvasnička, Tomáš ; Krištoufek, Ladislav (advisor) ; Avdulaj, Krenar (referee)
The main objective of this thesis is to analyze whether traded volume increases predictive power of volatility. We are mostly focused on Garman-Klass volatility estimator, which is more efficient than squared returns. Both univariate (AR, HAR, ARFIMA) and multivariate models (VAR, VAR-HAR) are used to find out if traded volume improves volatility forecasting. Furthermore, GARCH(1,1) both with and without traded volume is carried out and forecasted. All these methods are estimated on a basis of rolling window and during each step 1-day ahead forecast is computed. Final assessment is based on MAPE, RMSE and Mincer-Zarnowitz test of the out-of-sample forecasts, which are compared with the realized volatility. It turns out that traded volume slightly improves predictive power of the scrutinized models in case of FTSE 100 and IPC Mexico, contrary to Nikkei 225 and S&P 500 when a decrease of the predictive power is detected. Moreover, we observe that only HAR and VAR-HAR models are able to produce an unbiased forecast. As the evidence of the improvement is not conclusive and to maintain model parsimony, HAR model fitted by Garman-Klass volatility appears to be the best alternative in case of missing the realized volatility.
|
|
|
Stressed Value-at-Risk: Assessing extended Basel II regulation
Pižl, Vojtěch ; Šopov, Boril (advisor) ; Avdulaj, Krenar (referee)
This thesis investigates recently proposed enhancements to the Basel II market risk framework. The Basel Committee on Banking Supervision introduced a stressed Value-at-Risk, calculated from one year long period of financial stress, to be added to the current VaR as a reaction to the shortage in capital reserves of banks and thus their inability to cover extensive losses observed during the recent crisis. We present an empirical evidence that such an extension of the regulatory capital is not optimal. Firstly, supplementing an unconditional methods of VaR estimation, i.e. normal parametric VaR and historical simulation, by SVaR only lead to unnecessarily high capital requirements even in a low volatile periods whilst the same amount of capital during the crisis could be achieved using either the conditional GARCH VaR with student's-t innovations or the volatility weighted historical simulation. Moreover, we showed that all unconditional methods fail to capture volatility clusters such as the 2008 crisis.
|
|
|
Comparison of Stock Market Volatilities in Central Eastern Europe and South Eastern Europe
Petrovski, Dragan ; Horváth, Roman (advisor) ; Princ, Michael (referee)
The thesis offers a study on the stock market volatility in the countries of Central Eastern Europe and South Eastern Europe. We provide a univariate GARCH modeling of the stock market indices PX, BUX, and WIG from the CEE region and CROBEX, BELEX-15, and MBI from the SEE region. Additionally, we present a bivariate GARCH models in order to examine the volatility transmissions and spillovers from the European equity market to the equity markets in CEE and SEE. Our results suggest higher persistence of volatility in the CEE countries than in SEE countries, significant leverage effect more evident in the CEE region than in the SEE region, and high synchronization in the volatility between the CEE equity markets and the European equity market. The multivariate GARCH results reveal certain statistically significant but small volatility spillovers from the European equity market to the equity market in Hungary, Poland, Serbia and Republic of Macedonia. The CEE equity markets record higher conditional correlation coefficient than the SEE countries towards the European equity market. In general, the CEE equity markets are a relatively homogenous group in terms of volatility, while the SEE equity markets are a diversified group in terms of volatility with low synchronization and correlation with the...
|
guest ::
