Este trabajo de investigación examina el impacto de la volatilidad del tipo de cambio real, como proxy de la incertidumbre cambiaria, en el desempeño de las exportaciones totales para un panel de países de América Latina en el periodo 1989-2018. Se utilizan las variables como brecha de las exportaciones, brecha del tipo de cambio real, brecha del producto bruto interno, la brecha de la demanda mundial y la brecha de los término de intercambio. Asimismo, se estima el comportamiento de la volatilidad del tipo de cambio real modelizándola a través de modelos GARCH. Se estima un modelo panel de Vectores Autorregresivos para una muestra equilibrada de cinco países de América Latina (Argentina, Brasil, Chile, México y Perú) para el periodo 1989-2018. Los resultados sugieren que la volatilidad del tipo de cambio real tiene un efecto negativo en las exportaciones de los países seleccionados. Adicionalmente, esta investigación es relevante porque proporciona evidencia empírica de países con diferentes características económicas para comprender el efecto de las variaciones del tipo de cambio real en el desempeño de las exportaciones y, por ende, en la estabilidad del crecimiento económico. / This research work examines the impact of real exchange rate volatility, as a proxy for exchange rate uncertainty, on the performance of total exports for a panel of Latin American countries in the period 1989-2018. Variables such as the export gap, the real exchange rate gap, the gross domestic product gap, the world demand gap, and the trade terms gap are used. Likewise, the behavior of the volatility of the real exchange rate is estimated by modeling it through GARCH models. A panel model of Autoregressive Vectors is estimated for a balanced sample of five Latin American countries (Argentina, Brazil, Chile, Mexico, and Peru) for the period 1989-2018. The results suggest that the volatility of the real exchange rate has a negative effect on the exports of the selected countries. Additionally, this research is relevant because it provides empirical evidence from countries with different economic characteristics to understand the effect of variations in the real exchange rate on export performance and, therefore, on the stability of economic growth. / Trabajo de investigación

L'objectif de cette thèse est d’étudier à côté du risque défaut, le rôle spécifique des risques de volatilité et de co-volatilité dans la formation des taux longs dans la zone euro. On propose en particulier un modèle théorique de choix de portefeuille à deux pays permettant d’évaluer la contribution des primes de risque de volatilité aux processus de contagion et de fuite vers la qualité dans différents épisodes de la crise de la dette souveraine. Ce modèle permet également d’analyser le rôle des achats d’actifs (QE) de la BCE sur l’équilibre des marchés obligataires. Nos tests empiriques suggèrent que les programmes QE de la BCE à partir de mars 2015 n’ont fait qu’accélérer « une défragmentation » des marchés obligataires de la zone euro, apparue plus tôt dans la crise, dès la mise en place de l’OMT. / This thesis examines the specific role of volatility risks and co-volatility in the formation of long-term interest rates in the euro area. In particular, a two-country theoretical portfolio choice model is proposed to evaluate the volatility risk premia and their contribution to the contagion and flight to quality processes. This model also provides an opportunity to analyze the ECB's role of asset purchases (QE) on the equilibrium of bond markets. Our empirical tests suggest that the ECB's QE programs from March 2015 have accelerated the "defragmentation" of the euro zone bond markets.

Cette thèse présente trois contributions indépendantes. La première partie se concentre sur la modélisation de la moyenne conditionnelle des rendements du marché actions : le rendement espéré du marché. Ce dernier est souvent modélisé à l'aide d'un processus AR(1). Cependant, des études montrent que lors de mauvaises périodes économiques la prédictibilité des rendements est plus élevée. Etant donné que le modèle AR(1) exclut par construction cette propriété, nous proposons d'utiliser un modèle CIR. Les implications sont étudiées dans le cadre d'un modèle espace-état bayésien. La deuxième partie est dédiée à la modélisation de la volatilité des actions et des volumes de transaction. La relation entre ces deux quantités a été justifiée par l'hypothèse de mélange de distribution (MDH). Cependant, cette dernière ne capture pas la persistance de la variance, à la différence des spécifications GARCH. Nous proposons un modèle à deux facteurs combinant les deux approches, afin de dissocier les variations de volatilité court terme et long terme. Le modèle révèle plusieurs régularités importantes sur la relation volume-volatilité. La troisième partie s'intéresse à l'analyse des stratégies d'investissement optimales sous contrainte «drawdown ». Le problème étudié est celui de la maximisation d'utilité à horizon fini pour différentes fonctions d'utilité. Nous calculons les stratégies optimales en résolvant numériquement l'équation de Hamilton-Jacobi-Bellman, qui caractérise le principe de programmation dynamique correspondant. En se basant sur un large panel d'expérimentations numériques, nous analysons les divergences des allocations optimales / This PhD thesis presents three independent contributions. The first part is concentrated on the modeling of the conditional mean of stock market returns: the expected market return. The latter is often modeled as an AR(1) process. However, empirical studies have found that during bad times return predictability is higher. Given that the AR(1) model excludes by construction this property, we propose to use instead a CIR model. The implications of this specification are studied within a flexible Bayesian state-space model. The second part is dedicated to the modeling of stocks volatility and trading volume. The empirical relationship between these two quantities has been justified by the Mixture of Distribution Hypothesis (MDH). However, this framework notably fails to capture the obvious persistence in stock variance, unlike GARCH specifications. We propose a two-factor model of volatility combining both approaches, in order to disentangle short-run from long-run volatility variations. The model reveals several important regularities on the volume-volatility relationship. The third part of the thesis is concerned with the analysis of optimal investment strategies under the drawdown constraint. The finite horizon expectation maximization problem is studied for different types of utility functions. We compute the optimal investments strategies, by solving numerically the Hamilton–Jacobi–Bellman equation, that characterizes the dynamic programming principle related to the stochastic control problem. Based on a large panel of numerical experiments, we analyze the divergences of optimal allocation programs

[pt] A presente tese trata da estimação do risco e da precificação de ativos financeiros, de medidas que buscam estimar como os agentes de mercado estão avaliando a política monetária, bem como da inter-relação entre o mercado acionário e a política monetária. Esta inter-relação é representada pela estimação da reação do mercado acionário às mudanças na política monetária. O primeiro trabalho implementa dois recentes modelos de estimação de volatilidade que utilizam dados de alta frequência. O modelo Auto-Regressivo Heterogêneo (HAR) e o modelo Componente (2-Comp) são estimados e os resultados são comparados com os encontrados pelas estimações que utilizam a família de modelos Auto-Regressivos com Heteroscedasticidade Generalizados (GARCH). Durante o período analisado, os modelos que usam dados intradiários obtiveram melhores previsões de retornos dos ativos avaliados, tanto dentro como fora da amostra, confirmando assim que esses modelos possuem informações importantes para uma série de agentes econômicos. No trabalho seguinte se estima a credibilidade da política monetária implementada pelo Banco Central do Brasil - BCB nos últimos dez anos. Esta credibilidade foi estimada por meio de implementação do filtro de Kalman em medidas derivadas de expectativas inflacionárias de pesquisa ao consumidor, da pesquisa Focus do BCB e de curvas de juros dos títulos governamentais. Os resultados fornecem evidências da existência de três movimentos da credibilidade inflacionária estimada pela medida implícita e pela Focus no período analisado: (i) cedeu fortemente em meados de 2008, durante o momento mais crítico da Crise Subprime; (ii) relativa estabilidade entre o início de 2009 e meados de 2010 (meados de 2013, pela medida Focus); (iii) uma tendência de queda a partir de então, quando houve uma taxa real de juros abaixo da mínima compatível com a meta de inflação. Já a credibilidade inflacionária estimada a partir de pesquisa ao consumidor apresentou um comportamento mais errático que as demais, apresentando uma tendência de queda mais intensa a partir do início de 2013 e permanecendo em patamares próximos a zero desde então. Ao mesmo tempo, os resultados indicam que alterações da inflação são importantes para a previsão da credibilidade estimada a partir de pesquisa ao consumidor, validando sua característica backward looking e de ser formada a partir de expectativa adaptativa dos consumidores. A metodologia adotada possibilita desenvolver estimativas em tempo real do grau desta credibilidade e retornar avaliação quantitativa sobre a consistência da política monetária em um ambiente de metas de inflação. Ele contribui para a literatura existente ao implementar o teste de credibilidade de Svensson (1993) e o estender dentro de um arcabouço econométrico de espaço de estado, permitindo a estimação probabilística do grau de credibilidade da política monetária implementada pela autoridade monetária brasileira no período analisado. Finalmente, o terceiro e último trabalho é um estudo empírico da relação entre a política monetária, implementada pelo BCB, e o mercado de ações brasileiro. Utilizando a metodologia de Estudo de Eventos, analisa-se o efeito dos componentes esperados e não esperados das decisões de política monetária nos retornos do Índice Bovespa e de trinta e cinco ações de diferentes empresas. Os resultados fornecem evidências de que a política monetária possui um efeito significativo no mercado acionário, sendo que o evento de reversão na direção da política monetária tende a potencializar a resposta deste mercado. A análise no nível setorial indica que o setor de consumo cíclico é o mais afetado por esta política, enquanto os setores de utilidade pública e de petróleo, gás e biocombustíveis não são afetados significativamente. Os ativos individuais respondem de forma bastante heterogênea à política monetária, porém, ao se utilizar os retornos anormais destes ativos, identificou-se uma forte redução na intensidade e no número de empresas impactadas pela política monetária. Além disso, a surpresa monetária é explicada por variações não esperadas da taxa de desemprego, do índice de produção industrial e do IPCA, sendo Granger causada por variações não esperadas do índice de produção industrial, indicando a importância desta variável para a previsão da política monetária. / [en] This present thesis discusses the estimation of risk and of financial assets pricing, the measures that seek to estimate how the market players are evaluating the monetary policy, as well as the inter-relationship between the stock market and monetary policy. This interrelation is represented by the estimation of the stock market s reaction to changes in monetary policy. The first essay implements the estimation of two recent volatility models using high-frequency data. Heterogeneous Autoregressive model (HAR) and the Component model (2-Comp) are estimated and the results are compared with those found by estimations using the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) family models. During the analyzed period, the models using intraday data obtained better forecasts of asset returns valued both in-sample and out-of-sample, thus confirming that these models have important information for the economic agents. The next essay estimates the credibility of monetary policy implemented by the Central Bank of Brazil - BCB in the last ten years. This credibility was estimated by the use of Kalman filter on measures of inflation expectations derived from the consumer survey, the Focus survey from BCB and on the yield curves of government bonds. The results provide evidence of the existence of three changes on inflationary credibility in the analyzed period: (i) sharp downturn in mid-2008; (ii) relative stability between early 2009 and mid-2010 (mid-2013, for Focus measure); (iii) a downward trend since then, when there was a real interest rate below the minimum compatible with the inflation target. Besides, inflationary credibility estimated from the consumer pooling showed a more erratic behavior than the others, with a tendency to fall more intensely from the beginning of 2013 and remaining at levels close to zero since then. At the same time, the results indicate that inflation changes are important for the prediction of the credibility estimated from consumer pooling, validating its backwardated characteristic and its construction from adaptive consumer expectations. The adopted methodology enables to develop real-time estimates of BCB credibility and to return quantitative assessment of the consistency of monetary policy on an inflation target regime. This work adds to the existing literature in implementing Svensson credibility test (1993) and in extending it within an econometric framework of state space, allowing the probabilistic estimation of the degree of credibility of the monetary policy implemented by the Brazilian monetary authority during the analyzed period. Finally, the third and final essay is an empirical study of the relationship between monetary policy, implemented by the BCB, and the Brazilian stock market. Using the Event Study methodology, this essay analyzes the effect of expected and unexpected components of monetary policy decisions on the Bovespa index returns and on thirty-five different stock returns. The results provide evidence that monetary policy has a significant effect on the stock market returns, and the reversal event in the direction of monetary policy tends to enhance the response of the stock market. The analysis on a sectorial basis indicates that the cyclical consumer sector is the most affected by this policy, while the public utility and the oil, gas and biofuels sectors are not significantly affected. Individual assets respond in a very heterogeneous way to monetary policy. However, when using the abnormal returns, we identified a strong reduction in the intensity and in the number of companies affected by monetary policy. Furthermore, monetary surprise is explained by unexpected variations in the unemployment rate, in the industrial production index and in the CPI. Nonetheless, monetary surprise is Granger caused by unexpected variations in the industrial production index, indicating the importance of this variable for monetary policy forecasting.

Financial institutions manage numerous portfolios whose risk must be managed continuously, and the large amounts of data that has to be processed renders this a considerable effort. As such, a system that autonomously detects anomalies in the risk measures of financial portfolios, would be of great value. To this end, the two econometric models ARMA-GARCH and EWMA, and the two machine learning based algorithms LSTM and HTM, were evaluated for the task of performing unsupervised anomaly detection on the streaming time series of portfolio risk measures. Three datasets of returns and Value-at-Risk series were synthesized and one dataset of real-world Value-at-Risk series had labels handcrafted for the experiments in this thesis. The results revealed that the LSTM has great potential in this domain, due to an ability to adapt to different types of time series and for being effective at finding a wide range of anomalies. However, the EWMA had the benefit of being faster and more interpretable, but lacked the ability to capture anomalous trends. The ARMA-GARCH was found to have difficulties in finding a good fit to the time series of risk measures, resulting in poor performance, and the HTM was outperformed by the other algorithms in every regard, due to an inability to learn the autoregressive behaviour of the time series. / Finansiella institutioner hanterar otaliga portföljer vars risk måste hanteras kontinuerligt, och den stora mängden data som måste processeras gör detta till ett omfattande uppgift. Därför skulle ett system som autonomt kan upptäcka avvikelser i de finansiella portföljernas riskmått, vara av stort värde. I detta syftet undersöks två ekonometriska modeller, ARMA-GARCH och EWMA, samt två maskininlärningsmodeller, LSTM och HTM, för ändamålet att kunna utföra så kallad oövervakad avvikelsedetektering på den strömande tidsseriedata av portföljriskmått. Tre dataset syntetiserades med avkastningar och Value-at-Risk serier, och ett dataset med verkliga Value-at-Risk serier fick handgjorda etiketter till experimenten i denna avhandling. Resultaten visade att LSTM har stor potential i denna domänen, tack vare sin förmåga att anpassa sig till olika typer av tidsserier och för att effektivt lyckas finna varierade sorters anomalier. Däremot så hade EWMA fördelen av att vara den snabbaste och enklaste att tolka, men den saknade förmågan att finna avvikande trender. ARMA-GARCH hade svårigheter med att modellera tidsserier utav riskmått, vilket resulterade i att den preseterade dåligt. HTM blev utpresterad utav de andra algoritmerna i samtliga hänseenden, på grund utav dess oförmåga att lära sig tidsserierna autoregressiva beteende.

Doctor of Philosophy / Department of Economics / Lance J. Bachmeier / This dissertation investigates the long run and short run relationships between Saudi stock market returns and eight macroeconomic variables. We investigate the ability of these variables to predict the level and volatility of Saudi stock market returns. A wide range of Vector autoregression (VAR) and generalized autoregressive conditional heteroskedasticity (GARCH) models estimated and interpreted. A Johansen-Juselius cointegration test indicates a positive long run relationship between the Saudi stock price index and the M2 money supply, bank credit, and the price of oil, and a negative long run relationship with the M1 money supply, the short term interest rate, inflation, and the U.S. stock market. An estimated vector error correction model (VECM) suggests significant unidirectional short run causal relationships between Saudi stock market returns and the money supply and inflation. The VECM also finds a significant long run causal relationship among the macroeconomic variables in the system. The estimated speed of adjustment indicates that the Saudi stock market converges to the equilibrium within half a year. Granger causality tests show no causal relationship between Saudi stock market returns and the exchange rate. Impulse response function analysis shows no significant relationship between Saudi stock market returns and the macroeconomic variables. Forecast error variance decompositions suggest that 89% of the variation in Saudi stock market returns is attributable to its own shock, which implies that Saudi stock market returns are largely independent of the macroeconomic variables in the system. Finally, a GARCH-X model indicates a significant relationship between volatility of Saudi stock returns and short run movements of macroeconomic variables. Implications of this study include the following. (i) Prediction of stock market returns becomes more difficult as the volatility of the macroeconomic variables increases in the short run. (ii) Investors should look at the systematic risks revealed by these macroeconomic variables when structuring their portfolios and diversification strategies. (iii) Policymakers should seek to minimize macroeconomic fluctuations considering the effect of macroeconomic variables changes on the stock market when formulating economic policy.

股價波動度在財務金融領域一直受到高度的關切，雖然過去學者研究結論皆一致認同交易量與股價波動度具有顯著正向關係，交易量的變化可以視為相關訊息的傳遞，然而交易量能夠進一步分解為交易次數與平均交易規模，Jones, Kaul and Lipson（1994）等多位國內外學者也發現，交易次數較平均交易規模更具資訊內涵，指出交易次數才是造成股價波動的主要原因。然而有關交易次數方面之研究僅限於單一市場，隨著國內權證市場的興起，引發本研究進一步探討台股認購權證交易次數對標的股價波動度之影響，樣本選取2002年國內上市之所有個股型權證作為研究對象，以觀察是否交易次數較平均交易規模更具資訊內涵，並且代表市場臨時資訊的未預期交易次數較預期交易次數，對股價波動度更具顯著解釋能力。 實證結果發現，認購權證交易量確實能有效解釋標的股價波動的特性。然而認購權證交易次數較平均交易規模對股價波動度更具資訊內涵，並且權證交易次數對股價波動度的顯著正向關係，並不受到平均交易規模的影響，因此可以推論權證交易量所隱含的資訊內涵，其實是源於交易次數本身所造成，而非規模，此結論大致上支持策略型模型之說法。 若將交易活動變數進一步區分，更可發現權證交易次數不論預期與未預期，皆對股價波動度有正向顯著影響，並且權證未預期交易次數所蘊含之資訊內涵較預期交易次數為多，顯示股價波動度較易受到市場臨時資訊的影響，而透過交易行為傳遞到市場中，因此導致認購權證未預期交易次數對股價波動度具有高度正向的解釋能力。

The purpose of our study was to examine the relationship between the volatility of price multiples and the volatility of stock prices in the Swedish market from 2003 to 2012. Our focus was on the price-to-earnings ratio and the price-to-book ratio. Some previous studies showed a link between the price multiples and the volatility of stock prices, this made us question whether there should be a link between the volatility of the price multiples and the volatility of the stock prices. The importance of this subject is accentuated by the financial crisis, as we provide investors with information regarding the movements of price multiples and stock prices. Moreover, we test if the volatility of the price multiples can be used to create a prediction model for the volatility of stock prices. Also we fill the gap in the previous researches as there is no previous literature about this topic. We conducted a quantitative research using statistical tests, such as the correlation test and the linear regression test. For our data sample we chose the Sweden Datastream index. We first calculated the volatility using the GARCH model and then continued with our statistical tests. The results of our tests showed that there is a relationship between the volatility of the price multiples and the volatility of the stock prices in the Swedish market in the past ten years. Our findings show that the correlation coefficients vary across industries and over time in both strength and direction. The second part of our tests is concerned with the linear regression tests, mainly calculating the coefficient of determination. Our results show that the volatility of the price multiples do explain changes in the volatility of stock prices. Thus, the volatility of the P/E ratio and the volatility of the P/B ratio can be used in creating a prediction model for the volatility of stock prices. Nevertheless, we also find that this model is best suited when the economic situation is unstable (i.e. crisis, bad economic outlook) as both the correlation coefficient and the coefficient of determination had the highest values in the last five years, with the peak in 2008.

We examined the influence of news, related to the main central banks, on the conditional volatility of the stock returns of eighteen major European banks. We model their conditional volatility with GARCH, EGARCH and TGARCH models plugging in variables representing news. As a practical application we evaluate whether applying the news into the volatility modeling improves the performance of the Value-at-Risk (VaR) measure for given banks. The two types of news variables we use are constructed from the press releases of main central banks and from the search query at Factiva Dow Jones news database. The information contained in news is proxied by daily news counts. Using the EGARCH setup we are able to model individual volatility reaction functions of the banks' stock returns to different news variables. We show that the content, origin of the news and also the amount of news (news count) matter to the conditional volatility behavior. The results confirm that increase in the amount of media coverage causes increase in volatility. Certain news types have calming effect (speeches of the central banks' representatives) on volatility while others stir it (monetary news). Finally, we conclude that adding the news into the modeling only slightly improves the VaR out-of-sample performance.

American Depository Receipts (ADRs) represent shares of foreign firms that are issued and traded in the U.S. Since an ADR and its underlying shares represent ownership interest of the same firm, they should be perfect substitutes in a perfect market. However, market imperfections such as differences in information environment, liquidity, investment and trading restrictions, taxes, control right, corporate governance might make them less-than-perfect substitutes. These imperfections, on the other hand, also present opportunities for research. This dissertation consists of two essays on ADRs, both related to the effects of less-thanperfect information. Specifically, the first essay examines the return and volatility transfers between ADRs and their underlying home shares. Our investigation differs from the previous studies in that we cover substantially more countries and that we attempt to explain the variations in the extents of transfer effects both across firms and across countries. Various hypotheses are developed, based on the premise that barriers associated with trading, investments, and corporate governance would lower the extent or effectiveness of transfers. Overall, our empirical results support these hypotheses. The second essay takes the viewpoint of the issuing firms. Supposedly, an issuer's timing and dollar amount raised depend on the conditions of three markets: its home equity market, the U.S. equity market, and the currency market. From purely the standpoint of information accessibility, ADR issuers are likely to time their issues or set their amounts with respect to the conditions of the home equity market and/or currency market, with which they are more familiar. On the other hand, issuers typically employ the assistance of U.S. investment banks, and therefore they may be well-informed about the U.S. equity market. This is largely an empirical issue. Generally, our empirical results are mixed, but there is somewhat stronger evidence for the U.S. equity market being more important when setting the issue amount. There is also evidence that suggests regulations having influences on such activities.