[pt] Este trabalho objetiva, por meio da utilização de um modelo de paridade coberta de juros ajustada aos riscos país e demais riscos (sobretudo domésticos), verificar, estatisticamente, quais são os determinantes da taxa de juros brasileira para títulos públicos pré-fixados de longo prazo - no caso, as Notas do Tesouro Nacional Série F (NTN-Fs) de prazo aproximado de 10 anos, com vencimento em 2017. A variável dependente foi definida como a taxa de retorno das respectivas NTN-Fs, ao passo que as variáveis independentes ou explicativas foram a taxa livre de risco dos Treasuries norte-americanos de 10 anos, o prêmio de risco Brasil e o risco cambial. Os demais riscos (especialmente domésticos), por se tratarem do diferencial entre as NTN-Fs e as outras variáveis, encontram-se dentro do componente de termo do erro. Tendo em vista que as variáveis independentes possuem fortes relações de multicolinearidade - o que trouxe resultados visados para o coeficiente de determinação e aqueles individuais -, optou-se por rodar um modelo VAR e, a partir do mesmo, extrair os graus de endogeneidade de cada variável. Assim, foi possível observar o grau de importância e causalidade das variáveis individualmente e se o modelo estava corretamente especificado - ou seja, se a taxa de juros das NTN-Fs de longo prazo foi de fato explicada pelas demais variáveis. As principais ferramentas do modelo VAR - decomposição de variância e funções impulso-resposta - permitiram tirar importantes conclusões acerca dos impactos defasados de variações ou choques ocorridos nas variáveis independentes sobre a taxa de juros das NTN-Fs analisadas. Os resultados comprovaram que a taxa de juros das NTN-Fs é a variável mais endógena do modelo e, portanto, a dependente, além disso, mostrou que o risco cambial é a variável menos endógena, indicando sua importância cada vez menor na formação das taxas de juros de longo prazo no Brasil. A conclusão mais relevante, contudo, foi a evidência de que existe uma correlação negativa entre a taxa de juros livre de risco e a taxa dos títulos de longo prazo brasileiros, contrariando, pelo menos em 2007, a Teoria das Carteiras, que prevê uma relação positiva entre a taxa livre de risco e o retorno de um ativo. / [en] This study aims to verify statistically, through the utilization of an interest rate covered parity model adjusted to the country-risk and other risks (domestic, mainly), what are the determinants of Brazilian interest rates for long-term public fixed income securities - in this case, the so-called National Treasury Notes - Series F (NTN-Fs) with maturity in approximately 10 years, more precisely, in 2017. The dependent variable was defined as being the yield- to-maturity of the respective NTN-Fs, whereas the independent or explanatory variables were the risk-free rates of the US 10-year Treasuries, the Brazilian country-risk and the exchange rate risk. The other risks (especially domestic ones), as well as they reflect the differential between the NTN-Fs and the other variables, are one of the error term components. Given that the independent variables have strong multicollinearity - which brings biased results to the determination and individual coefficients -, we opted for using a VAR model and, based on it, obtain the endogenous degrees of each variable. Then, it was possible to observe the causality and importance level of the variables individually and if the model was correctly specified - that is, if the long-term NTN-Fs interest rates were in fact explained by the other variables. The main VAR model tools - which are the variance decomposition and the impulse-response functions - allowed us to make important conclusions about the delayed impacts of variations or shocks occurred in the independent variables over the analyzed NTN- Fs interest rates. The results proved that NTN-Fs interest rate is the most endogenous variable of the model and, therefore, the dependent one. The results also showed that the exchange rate risk is the less endogenous variable, suggesting it has a decreasing importance for the long-run interest rate building in Brazil. However, the most important conclusion was the evidence that there is a negative correlation between the risk-free rate and Brazilian long-run securities interest rates, opposing, at least in 2007, the Portfolio Theory, which foresees a positive relationship between the risk-free irate and the return of an asset.

Universidade Federal do Cearà / Neste estudo, pretende-se determinar um modelo de previsÃo mensal de curto prazo para a receita de ISSQN de Teresina. Para evidenciar este propÃsito servirÃo de suporte matemÃtico os modelos VAR e Box-Jenkins, a partir de sÃries histÃricas concernentes ao perÃodo de janeiro de 2002 a dezembro de 2006. ApÃs a estimaÃÃo dos modelos, propÃe-se um diagnÃstico para mensurar a capacidade inicialmente preditiva. Dentre os modelos manipulados temos o SARIMA (12,1,1)(0,0,12) o qual antecipadamente demonstrou ser mais robusto em relaÃÃo ao modelo VAR. Oportunamente à discussÃo de outras nuances internas ou à margem do trabalho, conclui-se que, o modelo com sÃries temporais, em funÃÃo de sua capacidade preditiva, pode se transformar em um instrumental consistente com vistas ao incremento da arrecadaÃÃo do ISSQN da Prefeitura de Teresina. / In this study, It is intended to determine a short-run monthly forecasting model for the ISSQN of Teresina city. In order for this purpose to be clear, the models VAR and Box-Jenkins will be of mathematical support, from historical series concerning the period of January 2002 to December 2006. After the estimation of the models, it is proposed a diagnosis to measure the initially predictive capacity. Among the models manipulated, we have SARIMA (12,1,1)(0,0,12), which has resulted most robust in advance concerning the VAR model. Propitiously to other internal or marginal nuances to the study, it is concluded, preliminarily, that the time series model due to its predictive capacity can become a consistent instrument targeting at the augment of the ISSQN collecting of Teresina City Administration.

No description available.

The aim of this diploma thesis is based on the empirical analysis to identify the relationship between the exchange rate and the interest rates in selected countries and verify the validity of the uncovered interest rate parity. In the first part, the author deals with basic theoretical and exchange rate determinants from a fundamental analysis point of view, which attempts to explain the causality between these two variables. The actual analysis was performed at three levels on monthly time series from 2010 to 2016. Graphical analysis was selected as the first stage of the analysis, also including verification of the validity of the Fisher International Effect. Later, regression and vector autoregressive analysis followed. However, the conclusions of the individual empirical parts show that the exchange rate is determined by many factors, not only by the interest rate differential, as assumed the theory of uncovered interest rate parity. These results are also related to the low quality of the estimated models. Uncovered interest rate parity has been confirmed in very few cases, but none of the monitored currency pairs has been validated at all three levels of empirical analysis at the same time. The work offers valuable insight into the trend appreciation or depreciation of the exchange rates at the positive interest rate differential in the selected period.

In this thesis the heterogeneity of regional real estate prices in United States is investigated. A high dimensional VAR model with additional exogenous predictors, originally introduced by \cite{fan11}, is adopted. In this framework, the common factor in regional house prices dynamics is explained by exogenous predictors and the spatial dependencies are captured by lagged house prices in other regions. For the purpose of estimation and variable selection under high-dimensional setting the concept of Penalized Least Squares (PLS) with different penalty functions (e.g. LASSO penalty) is studied in detail and implemented. Moreover, clustering methods are employed to identify subsets of statistical regions with similar house prices dynamics. It is demonstrated that these clusters are well geographically defined and contribute to a better interpretation of the VAR model. Next, we make use of the LASSO variable selection property in order to construct the impulse response functions and to simulate the prices behavior when a shock occurs. And last but not least, one-period-ahead forecasts from VAR model are compared to those from the Diffusion Index Factor Model by \cite{stock02}, a commonly used model for forecasts.

The aim of this paper is to analyse and compare inflation and its dynamics between two countries -- the Czech Republic and Germany -- applying a special kind of econometric models. The first part of this paper is dedicated to economic theory of inflation -- fundamental terms, measuring methods and its targeting. The monetary policy in the Czech Republic and Germany is also shortly introduced. Next chapter tries to describe the econometric concept which is used in this paper -- vector autoregression model (VAR model). In connection with the VAR models, Granger causality, impulse response function, cointegration and error correction model are mentioned as well. The empirical part includes application of selected models on real time series of macroeconomic indicators. Next to the interpretation of results, the forecasts are also implemented.

Cette thèse étudie les fluctuations macroéconomiques égyptiennes et compare leurs sources avec celles de certains pays du Moyen-Orient et Afrique du Nord (MENA). Un large éventail de méthodes économétriques sont utilisées pour examiner la synchronisation entre les cycles classiques et de croissance égyptiens et ceux de la région MENA, et de quantifier leurs sources de fluctuations ainsi que leurs réponses à ces sources de chocs. Nous ne trouvons aucune preuve de la synchronisation entre les cycles égyptiens et ceux de la région MENA et des pays développés. Les sources des fluctuations égyptiennes sont presque également réparties entre les chocs internes et étrangers, et les chocs du prix du pétrole semblent être le principal moteur de fluctuations de la production. En outre, la capacité de l'économie à contenir l'impact domestique des chocs externes négatifs à travers les chocs domestiques de l'offre et la demande est positive. / This thesis studies Egyptian macroeconomic fluctuations and compares their sources to those of some Middle East and North African (MENA) countries. A wide range of econometric methods are used to investigate the synchronization among Egyptian and MENA classical and growth cycles, and to quantify their sources of fluctuations along with their responses to these sources of shocks. We find no evidence of synchronization between Egyptian cycles and those of MENA and of developed countries. The sources of Egyptian macroeconomic fluctuations are almost equally divided among domestic and foreign shocks, and oil prices shocks appear to be the main driver behind output fluctuations. Moreover, domestic supply and demand shocks play a positive role in moderating negative foreign shocks affecting the economy.

Cities have adopted evolving urban digitization strategies, and most of those increasingly focus on data, especially in the field of public transportation. Transportation data have intuitively spatial and temporal characteristics, for they are often described with when and where the trips occur. Since a trip is often described with many attributes, the transportation data can be presented with a tensor, a container which can house data in $N$-dimensions. Unlike a traditional data frame, which only has column variables, tensor is intuitively more straightforward to explore spatio-temporal data-sets, which makes those attributes more easily interpreted. However, it requires unique techniques to extract useful and relatively correct information in attributes highly correlated with each other. This work presents a mixed model consisting of tensor decomposition combined with seasonal vector autoregression in time to find latent patterns within historical taxi data classified by types of taxis, pick-up and drop-off times of services in NYC, so that it can help predict the place and time where taxis are demanded. We validated the proposed approach using the experiment evaluation with real NYC tax data. The proposed method shows the best prediction among alternative models without geographical inference, and captures the daily patterns of taxi demands for business and entertainment needs.

This study will be investigating the relationship between short-term and long-term interest rates with the OMX30 stock return expressed in percentage, as well as the effect that the interest rates have on the stock return. The data used in this study has been collected from the dataprogram Datastream with monthly observations from January 2003 until December 2022 resulting in 240 different variables within all three factors over a period of 20 years. While performing OLS estimation, the result estimated by using R-studio shows a negative correlation between the interest rates and the percentage return of OMX30. Furthermore, the Granger causality test shows that the short-term interest rate does have an impact on the market whilst the long-term interest rate does not have any direct effect on the stock market in Sweden.

本文利用向量自我迴歸模型所得出來的殘差值來模擬未預期到的總體經濟訊息，以期限利差和一個月定存利率來捕捉殖利率曲線，以違約利差和股利收益率來描繪資產報酬的條件機率分布，本文實證未預期到的期限利差和未預期到的違約風險與淨值市價比因子和市值規模因子包含相同的訊息，因此後續檢驗這些能夠捕捉未來投資機會的總體經濟訊息比起Fama-French三因子模型是否對台灣股票橫斷面的平均報酬更具有解釋能力。 實證方法採用Fama-MacBeth(1973)兩階段迴歸方法，Fama-French三因子模型實證結果顯示台灣股票市場存在著負向的淨值市價比效果，但卻不存在著規模效果，這與國外一些學者研究1980年代之後規模效果逐漸消失的結論相同。在實證未預期到的總體經濟訊息模型時，由於被解釋變數為股票超額報酬率，因此常數項應該為不顯著的關係，但此假設強烈的被未預期到的總體經濟訊息模型拒絕，代表此模型可能遺漏了重要的解釋變數。因此，Fama-French 三因子模型對台灣股票橫斷面平均報酬率的解釋能力比未預期到的總體經濟訊息模型更佳。 / The Fama and French factors HML and SMB are correlated with innovations in variables that describe investment opportunities. I find that shocks to term spread and shocks to default spread have the same information with the Fama and French factors HML and SMB. This paper investigates whether a model that includes shocks to the aggregate dividend yield and term spread, default spread, and one-month deposit interest rate can explain the cross section of average return on Taiwan stock market as well as the Fama and French can. Using the Fama-MacBeth (1973) two steps cross-sectional regressions, I find there exists the negative book-to-market effect on Taiwan stock market, but the size effect disappears. Since the dependent variables in the regression is excess returns, the intercept of the cross-sectional regression should be zero. This hypothesis is strongly rejected in the case of the model includes shocks to the Macroeconomics variables and the market portfolio. It means this model omits some important variables, so the Fama and French three-factor model can explain the cross section of average returns better.