Denna uppsats ämnar undersöka hur volatilitetstransmissionen mellan sex aktiemarknader i världen ser ut och att utreda vilka aktiemarknader som har mest inflytande över den svenska börsens volatilitet. Uppsatsen syftar även till att utforska om graden av volatilitetsspridning ökat sedan IT-kraschen. Vid utförandet av denna studie används en ekonometrisk tvåstegsmodell inkluderande GARCH och VAR. Resultaten pekar på att det sprids volatilitet mellan aktiemarknaderna och att utländska innovationer står för en långvarig påverkan på den inhemska volatiliteten. Undersökningen visar att svenska börsen är den aktiemarknad som påverkas mest av utländska chocker och att den inte har någon nämnvärd påverkan på de andra aktiemarknaderna. Vidare påvisar resultaten att IT-kraschen lett till att utländska innovationer fått en större betydelse i Sverige liksom att den svenska börsens volatilitet blivit mer beroende av Nasdaqs.

Enligt teorin om öppen ränteparitet (UIP) ska den förväntade nominella växelkursförändringen motsvara räntedifferensen mellan två länder. I själva verket visar de flesta studier att teorin inte håller och att det förekommer ett signifikant negativt samband mellan variablerna istället för det positiva sambandet som följer av teorin (Froot&Thaler 1990, McCallum 1994). Även i denna uppsats konstateras ett negativt samband, vilket innebär att UIP kan förkastas för Sverige och USA under perioden 1994:1-2006:2. En amerikansk investerare som köper svenska statsskuldväxlar får således förutom en högre ränta även avkastning i form av en apprecierande växelkurs. I uppsatsen undersöks om avvikelsen från teorin kan förklaras utifrån förekomsten av en riskpremie för det mindre landet Sverige. Genom att använda den statistiska metoden GARCH-M kan det konstateras att växelkursens avkastning påverkas av dess volatilitet och således har effekt på avvikelsen från UIP. Tecknet för sambandet är dock felaktigt utifrån definitionen av en riskpremie. Det kan dock konstateras att det förekommer en riskpremie för Sverige som påverkas av inflationsdifferensen och statsskuldsdifferensen mellan länderna.

This study creates a model to predict short-term exchange rates as a combination of the relative purchasing power parity model (Grossman and Simpson 2011) and the interest power parity model. I then use the statistical techniques ARMA and GARCH to account for the variance of the terms. Previous works considered the effects of these models individually, but mine consider them in unison. I consider both in-sample and out-of-sample tests. I use data on five major exchange rates (JPY/USD, CAD/USD, CHF/USD, GBP/USD, and AUD/USD) sampled at a monthly frequency from 1989-2013. My model statistically significantly predicts these exchange rates over the January 2012 to January 2013 period.

This study attempts to quantify the shocks to a banking network and analyze the transfer of shocks through the network. We consider two sources of shocks: external shocks due to market and macroeconomic factors which impact the entire banking system, and idiosyncratic shocks due to failure of a single bank. The external shocks will be estimated by using two methods: (i) non-parametric simulation of the time series of shocks that occurred to the banking system in the past, and (ii) using the extreme value theory (EVT) to model the tail part of the shocks. The external shocks we considered in this study are due to exchange rate and treasury bill rate volatility. Also, an ARMA/GARCH model is used to extract iid residuals for this purpose. In the next step, the probability of the failure of banks in the system is studied by using Monte Carlo simulation. We calibrate the model such that the network resembles the Canadian banking system.

This study attempts to quantify the shocks to a banking network and analyze the transfer of shocks through the network. We consider two sources of shocks: external shocks due to market and macroeconomic factors which impact the entire banking system, and idiosyncratic shocks due to failure of a single bank. The external shocks will be estimated by using two methods: (i) non-parametric simulation of the time series of shocks that occurred to the banking system in the past, and (ii) using the extreme value theory (EVT) to model the tail part of the shocks. The external shocks we considered in this study are due to exchange rate and treasury bill rate volatility. Also, an ARMA/GARCH model is used to extract iid residuals for this purpose. In the next step, the probability of the failure of banks in the system is studied by using Monte Carlo simulation. We calibrate the model such that the network resembles the Canadian banking system.

El objetivo principal de esta Tesis es estudiar si la cobertura de carteras de renta variable utilizando contratos de futuro sobre índices bursátiles es más efectiva con ratios de cobertura constantes o dinámicos. El estudio se realiza para duraciones de la cobertura diaria y semanal. Se propone la utilización de modelos de Corrección de Error GARCH Bivariantes. Estos modelos permiten determinar ratios de cobertura que se ajustan frente a la llegada de noticias al mercado. También se analiza la existencia de un comportamiento diferencial del valor del ratio de cobertura alrededor de la fecha de vencimiento del contrato de futuro. Los resultados muestran que el ratio de cobertura debe ajustarse a la llegada de información frente a políticas de cobertura estáticas.Para determinar la conveniencia de realizar políticas de carácter dinámico, se utilizan medidas de efectividad que incorporan los costes de transacción en los que se incurre al ajustar la posición de futuros. El estudio de la efectividad se realiza desde una óptica ex-post y una ex-ante, más ajustada al verdadero proceso de decisión llevado a cabo por el inversor. La principal conclusión que se obtiene de la tesis es que con las políticas de cobertura dinámicas se producen resultados en los que se consigue reducir el riesgo de la posición cubierta, aunque su realización, en determinados casos, no es viable económicamente al considerar los costes de transacción en los que se incurre al ajustar las posiciones en el contrato de futuros.

The generalization from the univariate volatility model into a multivariate approach opens up a variety of modeling possibilities. This study aims to examine the performance of the two multivariate GARCH models BEKK and DCC, applied on ten years exchange rates data. Estimations and forecasts of the covariance matrix are made for the EUR/SEK and USD/SEK, whereby the  used in a practical application: 1-day and 10-day ahead historical simulated Value-at-Risk predictions for two theoretical portfolios, one equally weighted and one hedged, consisting of the two exchange rates. An univariate GARCH(1,1) approach is included in the Vale-at-Risk predictions to visualize the diversification effect in the portfolio. The conditional correlation forecasts are evaluated using three measures, OLS-regression, MAE and RMSE, based on an one year evaluation period of intraday data. The Value-at-Risk estimates are evaluated with the backtesting method introduced by Kupiec (1995). The results indicate that the BEKK model performs relatively better than the DCC model, and both these models perform better than the univariate GARCH(1,1) model.

We used neural-network based modelling to generalize the linear econometric return models and compare their out-of-sample predictive ability in terms of different performance measures under three density specifications. As error measures we used the likelihood values on the test sets as well as standard volatility measures. The empirical analysis was based on return series of stock indices from different financial markets. The results indicate that for all markets there was found no improvement in the forecast by non-linear models over linear ones, while nongaussian models significantly dominate the gaussian models with respect to most performance measures. The likelihood performance measure mostly favours the linear model with Student-t distribution, but the significance of its superiority differs between the markets. (author's abstract) / Series: Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

No description available.

Since the Bretton Woods System collapsed, the volatility of the exchange rate return has been an important and concerned issue in financial domain. The purpose of this paper is to investigate the empirical relevance of stricture breaks for the volatility of the exchange rate return, and we use both in-sample and out-of-sample tests. GARCH(1,1) Model is considered to be the representative quantitative method for analyzing the volatility of asset returns, as a result, we picked GARCH(1,1) as natural benchmarks in this article. In addition, we cogitated the structure breaks in this paper, and used ICSS(Iterated Cumulative Sums of Squares) algorithm to test the points of structural breaks. The results of empirical analysis show that there are significant evidences of structural breaks in the unconditional variance for six of eight US exchange rate return series, which implying unstable GARCH processes for these exchange rates. We also find those competing models that accommodating structural breaks will have higher predictive ability. Pooling forecasts from different models that allow for structural breaks in volatility appears to offer a reliable method for improving volatility forecast accuracy given the uncertainty surrounding the timing and size of the structural breaks.