This thesis consists of four essays, three in the field of random effects models and one in the field of GARCH. The first essay in this thesis, ''Maximum likelihood based inference in the two-way random effects model with serially correlated time effects'', considers maximum likelihood estimation and inference in the two-way random effects model with serial correlation. We derive a straightforward maximum likelihood estimator when the time-specific component follow an AR(1) or MA(1) process. The estimator is also easily generalized to allow for arbitrary stationary and strictly invertible ARMA processes. In addition we consider the model selection problem and derive tests of the null hypothesis of no serial correlation as well as tests for discriminating between the AR(1) and MA(1) specifications. A Monte-Carlo experiment evaluates the finite-sample properties of the estimators, test-statistics and model selection procedures. The second essay, ''Asymptotic properties of the maximum likelihood estimator of random effects models with serial correlation'', considers the large sample behavior of the maximum likelihood estimator of random effects models with serial correlation in the form of AR(1) for the idiosyncratic or time-specific error component. Consistent estimation and asymptotic normality is established for a comprehensive specification which nests these models as well as all commonly used random effects models. The third essay, ''Specification and estimation of random effects models with serial correlation of general form'', is also concerned with maximum likelihood based inference in random effects models with serial correlation. Allowing for individual effects we introduce serial correlation of general form in the time effects as well as the idiosyncratic errors. A straightforward maximum likelihood estimator is derived and a coherent model selection strategy is suggested for determining the orders of serial correlation as well as the importance of time or individual effects. The methods are applied to the estimation of a production function using a sample of 72 Japanese chemical firms observed during 1968-1987. The fourth essay, entitled ''A simple efficient GMM estimator of GARCH models'', considers efficient GMM based estimation of GARCH models. Sufficient conditions for the estimator to be consistent and asymptotically normal are established for the GARCH(1,1) conditional variance process. In addition efficiency results are obtained for a GARCH(1,1) model where the conditional variance is allowed to enter the mean as well. That is, the GARCH(1,1)-M model. An application to the returns to the SP500 index illustrates. / <p>Diss. Stockholm : Handelshögskolan, 2001</p>

In this paper the performance of classical approaches and GARCH family models are evaluated and compared in estimation one-step-ahead VaR. The classical VaR methodology includes historical simulation (HS), RiskMetrics, and unconditional approaches. The classical VaR methods, the four univariate and two multivariate GARCH models with the Student’s t and the normal error distributions have been applied to 5 stock indices and 4 portfolios to determine the best VaR method. We used four evaluation tests to assess the quality of VaR forecasts: -                     Violation ratio -                     Kupiec’s test -                     Christoffersen’s test -                     Joint test The results point out that GARCH-based models produce far more accurate forecasts for both individual and portfolio VaR. RiskMetrics gives reliable VaR predictions but it is still substantially inferior to GARCH models. The choice of an optimal GARCH model depends on the individual asset, and the best model can be different based on different empirical data.

The objective for this master thesis is to investigate the possibility to predict the risk of stocks in financial markets. The data used for model estimation has been gathered from different branches and different European countries. The four data series that are used in the estimation are price series from: Münchner Rück, Suez-Lyonnaise des Eaux, Volkswagen and OMX, a Swedish stock index. The risk prediction is done with univariate GARCH models. GARCH models are estimated and validated for these four data series. Conclusions are drawn regarding different GARCH models, their numbers of lags and distributions. The model that performs best, out-of-sample, is the APARCH model but the standard GARCH is also a good choice. The use of non-normal distributions is not clearly supported. The result from this master thesis could be used in option pricing, hedging strategies and portfolio selection.

The purpose of this thesis is to identify the factors playing a key role in the determination of the Turkish stock market liquidity in aggregate terms in a time series context and discuss the joint dynamics of the market-wide liquidity with its selected determinants and the trade volume. The main determinants tested are the level of return, the return volatility and the monetary stance of the Central Bank of the Republic of Turkey. The expected positive relationship between the liquidity and the return is confirmed, while the negative effect of the volatility on liquidity appears one-week later. The behavior of various liquidity variables are also examined around the macroeconomic data announcement dates, during the 2008 financial crisis, and after the tick size change in the Istanbul Stock Exchange (ISE). The time series dynamics between the trade volume, return, volatility and the liquidity are put forward within the Vector Autoregression analysis framework. The GARCH modeling of the return series, which is an input to the liquidity model estimations, is a byproduct of this thesis. It is observed that the return series exhibits volatility clustering, persistence, leverage effects and mean reversion. In addition, while the level of the ISE market return decreased, the volatility of the return increased during the 2008 crisis. Accordingly, EGARCH model assuming normally distributed error terms and allowing a shift in the variance during the crisis period is chosen as the best model.

This thesis investigates the predictability of trading strategies in the European and American stock market from 2001 to 2013. More specific, we examine the indices CAC40, DAX, FTSE100, NASDAQ and S&P500 first with the simple moving averages, then with trading rules based on the forecasts of time – series models and finally with the combination of the technical trading rules and time –series models. The significance of the examined trading rules tested with standard t – tests. The standard tests results show that technical trading rules are the most profitable strategy, second follows the combined and then the time – series rules as the least profitable trading strategy related to buy – and – hold strategy. / Σκοπός της παρούσας εργασίας είναι η διερεύνηση της προβλεπτικής δυνατότητας στρατηγικών επενδύσεων που εφαρμόζονται στην Ευρωπαϊκή και Αμερικάνικη χρηματιστηριακή αγορά, για τη χρονική περίοδο 2001-2013. Πιο συγκεκριμένα θα εξετασθούν οι δείκτες CAC 40, DAX, FTSE 100, NASDAQ και S&P 500, με κανόνες κινητών μέσων όρων, με κανόνες που βασίζονται σε μοντέλα πρόβλεψης χρονολογικών σειρών και με κανόνες συνδυαστικών των δύο ανωτέρω. Οι παραπάνω στρατηγικές θα συγκριθούν με την στρατηγική διακράτησης (Buy-and-Hold), που έχει ορισθεί ως benchmark στρατηγική και η σημαντικότητα των αποτελεσμάτων θα εξετασθεί με στατιστικούς ελέγχους t-statistics.

Desde Markowitz (1952), a volatilidade tem ocupado um papel de grande importância dentro da moderna teoria das finanças. Durante muito tempo, a mensuração da volatilidade tem sido realizada a partir de dados diários. No entanto, a disponibilização de dados intradiários, somada à redução do custo de aquisição destes, tem permitido a criação de modelos baseados nestes dados, o que permite incorporar mais informação, e em teoria, proporcionar previsões mais eficientes em comparação aos modelos que incorporam dados diários apenas. Dessa forma, o objetivo foi verificar se a modelagem da volatilidade a partir da utilização de dados diários é mais eficiente que a modelagem a partir de dados diários em termos de previsão da volatilidade futura. Utilizou-se, para comparar os modelos, a lucratividade de operações estruturadas no mercado de derivativos entre janeiro e abril de 2011. Os resultados demonstram que tantos os modelos baseados em dados diários como intradiarios apresentaram resultados satisfatórios em termos de previsão da volatilidade futura, tendo, entretanto, os modelos intradiários apresentado mais consistentes se comparado aos modelos diários, além de serem mais simples de serem estimados. / Since Markowitz (1952), volatility has played a major role in modern finance theory. For a long time, the measurement of volatility has been made from daily data. However, the availability of intraday data, added to reduce of the cost of these has allowed the creation of models based on these data, which allows to incorporate more information, and, in theory, provide more efficient forecasts compared to models that incorporate daily data only. Thus, the objective was to verify if the modeling of volatility from the use of daily data is more efficient than the model from daily data in terms of forecasting future volatility. Was used to compare the models, the profitability of structured transactions in the derivatives market between January and April 2011. The results show that both daily and intraday models showed satisfactory results in terms of forecasting future volatility, with, however, higher consistent of intraday models compared to daily models, being simpler to estimated them too.

A estimação e previsão da volatilidade de ativos são de suma importância para os mercados financeiros. Temas como risco e incerteza na teoria econômica incentivaram a procura por métodos capazes de modelar a variância condicional que evolui ao longo do tempo. O objetivo central desta dissertação foi modelar via modelos ARCH – GARCH e modelos aditivos o índice do IBOVESPA e o ativo PETR4 para analisar a existência de correlação entre as volatilidades estimadas. A estimação da volatilidade dos ativos no método paramétrico foi realizada via modelos EGARCH; já para o método não paramétrico, utilizouse os modelos aditivos com 5 defasagens. / Volatility estimation and forecasting are very important matters for the financial markets. Themes like risk and uncertainty in modern economic theory have encouraged the search for methods that allow for modeling of time varying variances. The main objective of this dissertation was estimate through GARCH models and additive models of IBOVESPA and PETR4 assets; and analyzes the existence of correlation between volatilities estimated. We use EGARCH models to estimate through parametric methods and use additive models 5 to estimate non parametric methods.

O estudo da volatilidade dos retornos dos ativos ocupa um lugar de destaque dentro da moderna teoria de finanças. Tradicionalmente, os modelos empregados para a modelagem da volatilidade são estimados a partir de dados diários. No entanto, a recente disponibilidade de dados intradiários tem permitido a modelagem e a previsão da volatilidade dos ativos por meio da chamada variância realizada. Dessa forma, o objetivo principal da presente dissertação foi analisar como os modelos que incorporam dados intradiários se comportam, em termos de acurácia de previsão de volatilidade diária, em relação àqueles que utilizam apenas dados diários. Foram observados os comportamentos dos índices Ibovespa e S&P 500 durante o período de janeiro de 2006 a junho de 2009. Os resultados revelaram que o desempenho de previsão dos modelos estimados a partir de dados diários foi superior ao dos modelos de variância realizada para os dois índices. Buscou-se ainda comparar o comportamento dos modelos durante o período da crise de 2008. Novamente os resultados apontaram para uma melhor acurácia de previsão dos modelos que utilizaram apenas dados diários. / The study of volatility in asset returns is relevant within the modern theory of finance. Modeling volatility has been frequently based on daily data. Recent availability of intraday data has allowed volatility modeling and forecasting through the so called realized variance. The main objective of this master’s thesis was, therefore, to compare the accuracy of daily volatility forecasting between models that use either daily or intraday data. Returns during the period January 2006 to June 2009 on two indexes, the Ibovespa and the S&P 500, were used. Results showed that, for both indexes, forecasting based on daily data was superior to forecasting that used intraday returns. Comparison between models was also tested during the 2008 crisis. Similarly, results showed a better forecasting performance of daily data models.

As séries temporais financeiras são marcadas por comportamentos complexos e não-lineares. No mercado financeiro, além da trajetória das cotações, a sua variabilidade, representada pela volatilidade, consiste em importante informação para o mercado. Redes neurais são modelos não lineares flexíveis com capacidade de descrever funções de distintas classes, possuindo a propriedade de aproximadores universais. Este trabalho busca empregar redes neurais, especificamente Perceptron de múltiplas camadas com uma única camada escondida alimentada para frente (Feedforward Multilayer Perceptron), para a previsão da volatilidade. Mais ainda, é proposto um modelo híbrido que combina o modelo GARCH e redes neurais. Os modelos GARCH e redes neurais são estimados para duas séries financeiras: Índice S&P500 e cotações do petróleo tipo Brent. Os resultados indicam que a volatilidade aproximada por redes neurais é muito semelhante as estimativas dos tradicionais modelos GARCH. Suas diferenças são mais qualitativas, na forma de resposta da volatilidade estimada a choques de maior magnitude e sua suavidade, do que quantitativas, apresentando critérios de erros de previsão em relação a uma medida de volatilidade benchmark muito próximos. / The financial time series are characterized by complex and non-linear behaviors. In addition to the financial market trend in prices their variability or volatility, a risk estimate, is important information for the market players. Neural networks are flexible nonlinear models capable of describing functions of different classes, having the property of universal approximators. This paper employs neural networks, specifically one hidden layer feedforward Multilayer Perceptron, for volatility forecasting. Moreover, we propose a hybrid model that combines the GARCH model with neural networks. The GARCH and neural network models are estimated over two financial series: the S&P500 composite index and prices of Brent oil. The results indicate that the volatility approximated by neural networks is very similar to that estimated by the traditional GARCH models, while their differences are more qualitative than quantitative, with information content that differs from and complements each other for different market environments.

A estimação e previsão da volatilidade de ativos são de suma importância para os mercados financeiros. Temas como risco e incerteza na teoria econômica incentivaram a procura por métodos capazes de modelar a variância condicional que evolui ao longo do tempo. O objetivo central desta dissertação foi modelar via modelos ARCH – GARCH e modelos aditivos o índice do IBOVESPA e o ativo PETR4 para analisar a existência de correlação entre as volatilidades estimadas. A estimação da volatilidade dos ativos no método paramétrico foi realizada via modelos EGARCH; já para o método não paramétrico, utilizouse os modelos aditivos com 5 defasagens. / Volatility estimation and forecasting are very important matters for the financial markets. Themes like risk and uncertainty in modern economic theory have encouraged the search for methods that allow for modeling of time varying variances. The main objective of this dissertation was estimate through GARCH models and additive models of IBOVESPA and PETR4 assets; and analyzes the existence of correlation between volatilities estimated. We use EGARCH models to estimate through parametric methods and use additive models 5 to estimate non parametric methods.