03742ntm a22005537i 4500 000549438 CZ-PrVSE 20181009215422.0 m d cr n|||||||||| 181009s2018 xr fsbm 000 0 eng d NEZPRACOVANÝ IMPORT ABA006 cze ABA006 ABA006 rda Fičura, Milan vse2015859798 dis Modelování a Predikce Stochastické Volatility a Skoků eng Modelling and Forecasting of Stochastic Volatility and Jumps / Milan Fičura 2018 ?? stran : digital, PDF soubor Vedoucí práce: Jiří Witzany Disertační práce (Ph.D.)—Vysoká škola ekonomická v Praze. Fakulta financí a účetnictví, 2018 Obsahuje bibliografii Textový (vysokoškolská kvalifikační práce) Rok obhajoby 2018 The thesis reviews the most commonly used volatility forecasting models from the ARCH/GARCH, realized volatility and stochastic volatility forecasting frameworks, with the main focus being placed on Stochastic-Volatility Jump-Diffusion (SVJD) models, on the ways of how high-frequency power-variation estimators can be used in SVJD model setting, and on the use of Bayesian methods for the estimation of SVJD model parameters and latent states. SVJD-RV-Z class of models is developed, utilizing the realized variance for better estimation of the stochastic variances, and the non-parametric Z-Estimator for more accurate estimation of price jumps. Several adapted particle filters, specifically designed for latent-state filtering in SVJD models, are derived, and a Sequential Gibbs Particle Filter (SGPF) algorithm is developed for the sequential learning of their parameters. In the empirical study, four SVJD models (with intraday data, self-exciting jumps in prices and volatility, as well as multiple volatility components) are applied for the task of realized volatility forecasting on the time series of 7 foreign exchange rates and 10 ETF/ETN securities in the daily, weekly and monthly forecast horizon. The performance of the SVJD models is compared with 3 GARCH models (GARCH, EGARCH and GJRGARCH), 15 HAR model specifications (HAR, AHAR, SHAR, HARJ and HARQ), and 15 Echo State Neural Network (ESN) based volatility models developed by the author. The SVJD-RV-Z models with jumps in volatility and prices are shown to exhibit the highest out-sample predictive power, comparable to the best HAR and ESN model specifications. Způsob přístupu: Internet finance [obor disert. práce] disertace fd132024 czenas dissertations eczenas Price jumps SVJD models Realized volatility Z-Estimator Stochastic volatility Bayesian methods Particle filters Witzany, Jiří, 1966- vse2007429830 ths Kodera, Jan jx20050428029 opn Vysoká škola ekonomická v Praze. Fakulta financí a účetnictví kn20010709398 dgg https://insis.vse.cz/zp/66507/podrobnosti VŠKP v InSIS https://insis.vse.cz/zp/66507 Hlavní práce https://insis.vse.cz/zp/66507/posudek/vedouci Hodnocení vedoucího https://insis.vse.cz/zp/66507/posudek/oponent/58708 Oponentura https://insis.vse.cz/zp/66507/posudek/oponent/58709 Oponentura https://insis.vse.cz/zp/66507/podrobnosti dc:identifier NEPOSILAT VSKP vse66507 181006 66507