|
|
Analysis and modeling of network data traffic
Paukeje, Ján ; Novotný, Vít (referee) ; Růčka, Lukáš (advisor)
Theses deals with network traffic modeling focused on elaboration by time series analysis. The nature of network traffic is discussed above all http traffic. First three chapters are theoretical, which describes time series and basic models, linear AR, MA, ARMA, ARIMA and nonlinear ARCH. Other chapters define terms like self-similarity and long range dependence. It is demonstrated a failure of conventional models which cannot capture these specific properties of network data traffic. On the basis of study in chapter 6. is closely described the combined ARIMA/GARCH model and its parameter estimation procedure. Applied part of this theses deals with procedure of estimation and fitting the estimation model to observed network traffic. After an estimation a few future values are predicted on the basis of estimated model. These predicted values are consequently compared with real data.
|
|
|
Bitcoin volatility estimation
Bařina, Petr-Lev ; Pavláková Dočekalová, Marie (referee) ; Luňáček, Jiří (advisor)
Tato bakalářská práce se zaměřuje na ekonometrické modelování a predikci volatility Bitcoinu. První částí práce je teorie statistických vlastností časových řad a modely interpretující tyto vlastnosti. Praktická část je zaměřena na modelování, predikci a hodnocení přesnosti predikcí. Klíčovými modely jsou model klouzavého průměru, autoregresní model, ARCH a GARCH. Poslední částí je shrnutí výsledků a návrhy na zlepšení.
|
|
|
Šíření volatility na kryptoměnových trzích
Krampla, Dominik
This thesis investigated the identification of conditional volatility in cryptocurrency markets and explored how uncertainty spreads among various cryptocurrencies. Using GARCH family models, conditional volatility was modeled, and the DCC-GJR- GARCH(1,1) model was applied to identify the spread of conditional volatility, accounting for the impact of asymmetric shocks. The empirical analysis was based on high-frequency 15-minute data for five cryptocurrencies – Bitcoin, Ethereum, Ripple, Cardano, and Litecoin – from 23. April 2021 to 31. March 2022, with total number observations of 32 904 per cryptocurrency. The results suggest that uncertainty spreads most significantly between Bitcoin and Ethereum, while Ripple and Cardano are less affected by the spread of uncertainty from Bitcoin. The study also examines suitable combinations of cryptocurrency weights in various portfolio formation strategies, with the DCC-GJR-GARCH (1,1) strategy achieving the lowest risk.
|
|
|
Šíření podmíněné volatility na kryptoměnových trzích
Hořava, Martin
Hořava, M. Conditional volatility spillovers in the cryptocurrency markets. Diploma thesis. Brno: Mendel University, 2022. The purpose of this thesis was to identify conditional volatility in cryptocurrency markets and the mutual dynamic volatility spillover between individual assests. The literature review describes conditional volatility and methods of its estimation. In the empirical part, the DCC-GARCH model was used and the portfolio was optimized. The results showed that cryptocurrencies are higly interconnected, but can still be diversified. At the end of the thesis, specific recommendations for the portfolio managers are provided.
|
|
|
Central bank communication and exchange rates: High-frequency evidence
Suntychová, Petra ; Horváth, Roman (advisor) ; Komárek, Luboš (referee)
The GARCH analysis has been used to estimate the effect of central banks' announcements, posted on their official websites, on demands for the curren- cies they are taking care of, with a focus on the type of announcements re- leased. The announcement specifics observed were past-looking statements, and forward-looking statements, whether they were announcing a monetary policy, financial stability, or commenting on a political situation. The results have shown that announcements made by central banks, both European Central Bank and Czech National Bank, mostly have not significantly affected demands for their respective currencies with certain exceptions. Also, the results suggest that demand for the Euro currency is being affected by these announcements with a longer lag, and announcements made by the European Central Bank are having less impact than those of its Czech counterpart. Overall, it has been concluded that announcements posted on official websites are affecting currency demands less than other influencing factors. JEL Classification F12, F21, F23, H25, H71, H87 Keywords central bank, exchange rate, foreign exchange, GARCH Title Central bank communication and currency de- mand: GARCH Analysis
|
|
|
The Impact of News on Videogame Stock Market Prices and Volatility
Mertová, Veronika ; Čech, František (advisor) ; Kukačka, Jiří (referee)
The thesis investigates the impact of social media and news headline sentiment on stock prices, specifically comparing gaming firms to companies from other industries. Tweets and news headlines containing keywords referring to four selected gaming and four non-gaming companies were collected over 5 and 3 months, respectively. Both tweets and news collected came from the general users or media rather than focusing solely on financial ones. The data were aggregated into daily values. Daily stock price data were also collected for each examined company to derive returns and volatility. The data were analysed using a vector autoregression model in combination with Granger causality. The study found no significant differences between gaming and non-gaming sectors. The polarity of sentiment showed no effect on stock prices. However, when sentiment was divided into different emotions, some significance was observed, although the findings varied across individual firms regardless of their sectors. It was concluded that when using sentiment for market predictions, it is beneficial to either utilize specifically financial media or determine the specific type of sentiment that influences a particular stock. JEL Classification G14, G17, C32, C58 Keywords Tweets, News Headlines, Gaming Industry, Sentiment...
|
|
|
The Effects of Geopolitical Uncertainty on Selected Stock Markets
Černý, Ondřej ; Horváth, Roman (advisor) ; Šíla, Jan (referee)
This thesis examines the impact of geopolitical uncertainty on four selected stock markets. We analyse the effect on stock market volatility and returns using the GARCH and the EGARCH models and daily stock returns and GPR index value. Furthermore, using categorical indices GPA and GPT, we inspect whether the effect of uncertainty caused by threats differs from that caused by acts. Additionally, we examine whether the impact changed between the period before and after 9/11. The main findings from our results suggest that a rise in each of the risk indices, i.e. global GPR, GPA and GPT, increases the volatility of all of the stock markets and the returns of the two. Also, geopolitical threats negatively influence Hong Kong stock returns, whereas geopolitical acts do not impact them. Furthermore, the impact of at least one of the uncertainty on stock return or volatility changed in the case of all the selected stock markets. JEL Classification C22, C51, C52, C58, G10 Keywords GARCH, geopolitical risk, stock market volatil- ity, stock market returns Title The Effects of Geopolitical Uncertainty on Se- lected Stock Markets Author's e-mail 43885002@fsv.cuni.cz Supervisor's e-mail roman.horvath@fsv.cuni.cz
|
|
|
Correlation between stock and bond returns and it's determinants: Case of Fragile Five
Daldal, Cagatay ; Kočenda, Evžen (advisor) ; Čech, František (referee)
The correlation between stock market returns and government bond yields is helping investors to diversify their investments and hence, reducing their investment risk if the correlation between these asset classes is low or negative. However, the correlation measure is not solely sufficient for investors to diversify their risk considering that correlation between stock market returns and government bond yields and impacted by the same economic conditions. Therefore, it is important understand how correlation between stock market returns and government bond yields is developing over-time and which economic indicators impacting the correlation. The author contributes to the existing literature by modelling the time-varying correlation between stock marketreturnsand governmentbond yields.The currentresearch focused on Turkey,Brazil,South Africa, India and Indonesia. These countries were defined as Fragile Five in 2013 by Morgan Stanley because the currencies of these countries were under high pressure against United States Dollar and shared common vulnerability in their current account levels, inflation, unemployment rate and gross domestic product. These economic indicatorsof Fragile Five are used to determine if the correlation between stock market returns and government bond yields is impacted by...
|
|
|
Bitcoin volatility estimation
Bařina, Petr-Lev ; Pavláková Dočekalová, Marie (referee) ; Luňáček, Jiří (advisor)
Tato bakalářská práce se zaměřuje na ekonometrické modelování a predikci volatility Bitcoinu. První částí práce je teorie statistických vlastností časových řad a modely interpretující tyto vlastnosti. Praktická část je zaměřena na modelování, predikci a hodnocení přesnosti predikcí. Klíčovými modely jsou model klouzavého průměru, autoregresní model, ARCH a GARCH. Poslední částí je shrnutí výsledků a návrhy na zlepšení.
|
|
|
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.
|
guest ::
