Submitted by Marcus Rocha (marcus.bonaldi@gmail.com) on 2014-11-12T01:38:53Z No. of bitstreams: 1 Versão Final tese PDF.pdf: 5244046 bytes, checksum: ebbdc36061829e3c3c3043394222067c (MD5) / Approved for entry into archive by Viviane Alencar (viviane.alencar@fgv.br) on 2014-11-12T11:32:23Z (GMT) No. of bitstreams: 1 Versão Final tese PDF.pdf: 5244046 bytes, checksum: ebbdc36061829e3c3c3043394222067c (MD5) / Approved for entry into archive by Marcia Bacha (marcia.bacha@fgv.br) on 2014-11-13T13:53:37Z (GMT) No. of bitstreams: 1 Versão Final tese PDF.pdf: 5244046 bytes, checksum: ebbdc36061829e3c3c3043394222067c (MD5) / Made available in DSpace on 2014-11-13T13:53:46Z (GMT). No. of bitstreams: 1 Versão Final tese PDF.pdf: 5244046 bytes, checksum: ebbdc36061829e3c3c3043394222067c (MD5) Previous issue date: 2010-07-05 / This work investigates and analyzes the differences between inflation’s annual rates and the forecasts by economic agents, for a year ahead. The inflation index examined, were the IPCA, IPA-M, IGP-M and IGP-DI. For each agents preview, for each index, we performed a statistical analysis and time series analysis, by ARIMA model. Through this model we understood the forecast errors of economic agents by the past values of forecast errors in the past, besides the stochastic terms. / Este trabalho investiga e analisa as diferenças das taxas anuais de inflação realizadas com relação às previsões dos agentes econômicos do mercado para um ano à frente. Os índices analisados foram o IPCA, IPA-M, IGP-M e o IGP-DI. Referente à previsão dos agentes para cada índice, foi feito uma análise estatística e uma análise de séries temporais através do modelo ARIMA. Este último explicou o erro de previsão dos agentes econômicos através de valores passados, ou defasados, do próprio erro de previsão, além dos termos estocásticos.

Made available in DSpace on 2010-04-20T20:51:19Z (GMT). No. of bitstreams: 3 62683.pdf.jpg: 17681 bytes, checksum: f564240c011f73dddcf42bea315c0da7 (MD5) 62683.pdf: 1894862 bytes, checksum: c422f7726a9b5506aba70f338adc614d (MD5) 62683.pdf.txt: 93822 bytes, checksum: f4235a61461b415e2529bf47c8f256c1 (MD5) Previous issue date: 2005-02-15T00:00:00Z / A dissertação tem como principal objetivo a busca de evidências da existência de um componente determinístico no comportamento dos preços de certas ações negociadas na Bolsa de Valores de São Paulo (BOVESPA) e em índices amplos do mercado, tais como o Ibovespa e IBX e, como conseqüência, determinar se a Hipótese de Mercado Eficiente é válida para o mercado financeiro brasileiro. Um objetivo secundário é mostrar a aplicabilidade de técnicas interdisciplinares ao estudo de Finanças empíricas, técnicas essas que, desde sua incepção, já levam em consideração o fato de que os dados estudados não atendem ao requisito de normalidade e que as observações não são independentes entre si. Essa aplicabilidade já é largamente demonstrada em inúmeros estudos internacionais e diversas publicações no Brasil. Porém, o presente trabalho tentará aplicar uma estrutura analítica mais flexível e computacionalmente mais eficiente, utilizando ferramentas trazidas do campo da Teoria da Informação e avanços relativamente recentes da área. / The present work has as the main objective to search evidence towards the existence of a deterministic chaotic component in the behavior of the prices of certain stocks negotiated in the São Paulo Stock Exchange (BOVESPA) and important market indexes, as the Ibovespa and the IBX and, as a consequence, to verify the validity of the Efficient Market Hypothesis for the Brazilian financial market. A secondary objective is to show the viability of interdisciplinary techniques to the study of empirical financial data. Since their inception, those techniques were developed considering the fact that the studied series would not be compliant to the normality and independence assumptions. Even as the secondary objective is already met by a large number of academic literature, including some important Brazilian papers, the present work will try to apply a more up-to-date and efficient analytical structure, using tools brought from the field of Information Theory and relatively recent published results.

Orientador: Prof. Dr. Vinicius Cifú Lopes / Dissertação (mestrado) - Universidade Federal do ABC, Programa de Pós-Graduação em Mestrado Profissional em Matemática em Rede Nacional, 2016. / Inicia-se o presente trabalho apresentando ao leitor a necessidade de se apropriar profundamente dos conceitos relacionados às funções lineares e quadráticas, seu crescimento e decrescimento, estudos dos sinais e construção de seus respectivos gráficos, da resolução pelo método do varal para inequações-produto e inequações-quociente, que auxiliam na construção de gráficos de funções de graus maiores que dois, das variáveis e substituição de variáveis, bem como calcular e operar com polinômios, especialmente a divisão euclidiana e o algoritmo de Briot-Ruffini, para então estudar as sequências e séries numéricas. O estudo das séries de potências, desenvolvido no capítulo 5, é de fundamental importância na expansão do polinômio de Taylor, com suas aproximações sucessivas para as funções seno, cosseno entre outras, definidas por séries de potências e para a perfeita compreensão dos resultados presentes no capítulo final. / The present work begins by presenting to the reader the need to take a firm hold of the concepts related to linear and quadratic functions, their growth and decrement, studies of their signal and construction of their respective graphs, resolution by the factor method for product inequalities and quotient inequalities, which help constructing graphs of functions of degrees greater than two, variables and variable substitution, as well as to calculate and operate with polynomials, especially the Euclidean division and the Briot-Ruffini algorithm, and then to study the sequences and series numbers. The study of power series, developed in Chapter 5, has fundamental importance for the expansion of the Taylor polynomial, with its successive approximations for the functions sine, cosine among others, defined by power series, and for the perfect understanding of the results shown in the final chapter.

CAPES / Desenvolvemos um trabalho visando habilidades relacionadas à compreensão, investigação e a contextualização de situações problemas, caracterizando o pensar matemático na construção do conhecimento. Na medida em que abordamos situações matemáticas percebe-se o quanto é significativo ensinar e aprender. Tratamos a matemática financeira como um estudo de funções. Progressões, aritmética e geométrica, são tratadas como funções afim e exponencial, respectivamente, para um domínio discreto. Faz-se análise de gráficos e tabelas com o intuito de compreender e investigar situações de financiamentos. Através de uma pesquisa com a comunidade local orientamos os alunos quanto à importância de se ter uma educação financeira adequada para tomada de decisões. / We develop a job seeking skills related to the understanding, research and contextualization of problem situations, featuring mathematical thinking in knowledge construction. Insofar as situations mathematical approach realizes how teaching and learning is significant. We treat financial mathematics as a study of functions. Progressions, arithmetic and geometry are treated as, affine and exponential functions, respectively for discrete domain. It is analyzing graphs and tables in order to understand and investigate financing situations. Through a survey of the local community have the students about the importance of having a financial education for decision making.

Submitted by Ricardo Guedes (ricardobbgg@gmail.com) on 2013-01-16T03:10:17Z No. of bitstreams: 1 Dissertação.pdf: 832861 bytes, checksum: 53474ad22711938d64bf30b48c8d9ead (MD5) / Approved for entry into archive by Marcia Bacha (marcia.bacha@fgv.br) on 2013-01-29T12:48:49Z (GMT) No. of bitstreams: 1 Dissertação.pdf: 832861 bytes, checksum: 53474ad22711938d64bf30b48c8d9ead (MD5) / Made available in DSpace on 2013-01-29T12:58:46Z (GMT). No. of bitstreams: 1 Dissertação.pdf: 832861 bytes, checksum: 53474ad22711938d64bf30b48c8d9ead (MD5) Previous issue date: 2010-11-03 / The inclusion of higher moments in CAPM has been discussed in recent decades. This work performs an empirical test of the model extended to the third and fourth moments, in which the skewness and kurtosis are also priced. This test was based on Generalized Method of Moments (GMM) procedures, in which all the moment conditions derived from the theoretical model. The data used were the daily returns of the most liquid Brazilian stocks between 2004 and 2006. / A inclusão de momentos superiores no apreçamento de ativos do modelo CAPM vem sendo bastante discutido nas últimas décadas. Esse trabalho realiza um teste empírico para o modelo CAPM estendido para os 3o e 4o momentos, no qual as assimetrias e curtoses dos ativos também são apreçadas. O teste foi realizado utilizando o Método Generalizado dos Momentos (MGM), em que todas as condições de momento derivam do modelo teórico. Os dados utilizados foram os retornos diários das ações mais negociadas na Bovespa entre 2004 e 2006.

Submitted by Pedro Bogado (pedrobogado@gmail.com) on 2013-01-10T14:13:41Z No. of bitstreams: 1 PedroBogado_final.pdf: 351157 bytes, checksum: 8e8aaaca8adbafbbe0148af641564a29 (MD5) / Approved for entry into archive by Marcia Bacha (marcia.bacha@fgv.br) on 2013-01-29T16:26:40Z (GMT) No. of bitstreams: 1 PedroBogado_final.pdf: 351157 bytes, checksum: 8e8aaaca8adbafbbe0148af641564a29 (MD5) / Made available in DSpace on 2013-01-29T16:28:57Z (GMT). No. of bitstreams: 1 PedroBogado_final.pdf: 351157 bytes, checksum: 8e8aaaca8adbafbbe0148af641564a29 (MD5) Previous issue date: 2010-11-03 / The identification problem of supply and demand equations for testing the bank lending channel has been discussed in recent decades. This work evaluates the identification strategy carried out in a VECM setting to determine if there is empirical evidence of a bank lending channel in the transmission of monetary policy in Brazil. Monthly aggregate data was used for the period 2001 through 2010. / O problema da identificação de equações de oferta e demanda de crédito para verificação da existência do canal de crédito tem sido sendo bastante discutido nas últimas décadas. Este trabalho avalia a estratégia de identificação via estimação de um modelo de um Modelo Vetorial de Correção de Erros para determinar a relevância do canal de crédito no Brasil. Foram utilizados dados agregados mensais compreendendo o período de 2001 até 2010.

On étudie la correspondance de Howe entre la catégorie de représentations complexes de G et celle de G’, pour des paires duales irréductibles (G,G’) définis sur des corps finis de caractéristique impaire. On établit la compatibilité entre la correspondance de Howe et les séries arbitraires de Harish-Chandra. On démontre comment obtenir des sous-représentations extrémales (i.e. minimales et maximales) de l’image d’une représentation irréductible unipotente de G. Finalement, on démontre comment l’étude de la correspondance de Howe entre séries d’Harish-Chandra arbitraires peut être ramenée à l’étude des séries unipotentes, et on utilise ceci pour étendre nos résultats sur les représentations extrémales aux représentations irréductibles arbitraires (i.e. pas forcément unipotentes) de G. / We study the Howe correspondence between the category of complex representations of G and that of G’, for irreducible dual pairs (G,G’) over finite fields of odd characteristic. We establish the compatibility between the Howe correspondence and arbitrary Harish-Chandra series. We define and prove the existence of extremal (i.e. minimal and maximal) irreducible sub-representations from the image of irreducible unipotent representations of G. Finally, we prove how the study of the Howe correspondence between arbitrary Harish-Chandra series can be brought to the study of unipotent series, and use this to extend our results on extremal representations to arbitrary (i.e. not necessarily unipotent) irreducible representations of G.

Les séries temporelles deviennent omniprésentes dans la vie moderne et leur analyse de plus en plus difficile compte tenu de leur taille. L’analyse des grandes séries de données implique des tâches telles que l’appariement de modèles (motifs), la détection d’anomalies, l’identification de modèles fréquents, et la classification ou le regroupement (clustering). Ces tâches reposent sur la notion de similarité. La communauté scientifique a proposé de plusieurs techniques, y compris de nombreuses mesures de similarité pour calculer la distance entre deux séries temporelles, ainsi que des techniques et des algorithmes d’indexation correspondants, afin de relever les défis de l’évolutivité lors de la recherche de similarité.Les analystes, afin de s’acquitter efficacement de leurs tâches, ont besoin de systèmes d’analyse visuelle interactifs, extrêmement rapides, et puissants. Lors de la création de tels systèmes, nous avons identifié deux principaux défis: (1) la perception de similarité et (2) la recherche progressive de similarité. Le premier traite de la façon dont les gens perçoivent des modèles similaires et du rôle de la visualisation dans la perception de similarité. Le dernier point concerne la rapidité avec laquelle nous pouvons redonner aux utilisateurs des mises à jour des résultats progressifs, lorsque les temps de réponse du système sont longs et non interactifs. Le but de cette thèse est de répondre et de donner des solutions aux défis ci-dessus.Dans la première partie, nous avons étudié si différentes représentations visuelles (Graphiques en courbes, Graphiques d’horizon et Champs de couleur) modifiaient la perception de similarité des séries temporelles. Nous avons essayé de comprendre si les résultats de recherche automatique de similarité sont perçus de manière similaire, quelle que soit la technique de visualisation; et si ce que les gens perçoivent comme similaire avec chaque visualisation s’aligne avec différentes mesures de similarité. Nos résultats indiquent que les Graphes d’horizon s’alignent sur des mesures qui permettent des variations de décalage temporel ou d’échelle (i.e., ils promeuvent la déformation temporelle dynamique). En revanche, ils ne s’alignent pas sur des mesures autorisant des variations d’amplitude et de décalage vertical (ils ne promeuvent pas des mesures basées sur la z-normalisation). L’inverse semble être le cas pour les Graphiques en courbes et les Champs de couleur. Dans l’ensemble, nos travaux indiquent que le choix de la visualisation affecte les schémas temporels que l’homme considère comme similaires. Donc, la notion de similarité dans les séries temporelles est dépendante de la technique de visualisation.Dans la deuxième partie, nous nous sommes concentrés sur la recherche progressive de similarité dans de grandes séries de données. Nous avons étudié la rapidité avec laquelle les premières réponses approximatives et puis des mises à jour des résultats progressifs sont détectées lors de l’exécuton des requêtes progressives. Nos résultats indiquent qu’il existe un écart entre le moment où la réponse finale s’est trouvée et le moment où l’algorithme de recherche se termine, ce qui entraîne des temps d’attente gonflés sans amélioration. Des estimations probabilistes pourraient aider les utilisateurs à décider quand arrêter le processus de recherche, i.e., décider quand l’amélioration de la réponse finale est improbable. Nous avons développé et évalué expérimentalement une nouvelle méthode probabiliste qui calcule les garanties de qualité des résultats progressifs de k-plus proches voisins (k-NN). Notre approche apprend d’un ensemble de requêtes et construit des modèles de prédiction basés sur deux observations: (i) des requêtes similaires ont des réponses similaires; et (ii) des réponses progressives renvoyées par les indices de séries de données sont de bons prédicteurs de la réponse finale. Nous fournissons des estimations initiales et progressives de la réponse finale. / Time series are becoming ubiquitous in modern life, and given their sizes, their analysis is becoming increasingly challenging. Time series analysis involves tasks such as pattern matching, anomaly detection, frequent pattern identification, and time series clustering or classification. These tasks rely on the notion of time series similarity. The data-mining community has proposed several techniques, including many similarity measures (or distance measure algorithms), for calculating the distance between two time series, as well as corresponding indexing techniques and algorithms, in order to address the scalability challenges during similarity search.To effectively support their tasks, analysts need interactive visual analytics systems that combine extremely fast computation, expressive querying interfaces, and powerful visualization tools. We identified two main challenges when considering the creation of such systems: (1) similarity perception and (2) progressive similarity search. The former deals with how people perceive similar patterns and what the role of visualization is in time series similarity perception. The latter is about how fast we can give back to users updates of progressive similarity search results and how good they are, when system response times are long and do not support real-time analytics in large data series collections. The goal of this thesis, that lies at the intersection of Databases and Human-Computer Interaction, is to answer and give solutions to the above challenges.In the first part of the thesis, we studied whether different visual representations (Line Charts, Horizon Graphs, and Color Fields) alter time series similarity perception. We tried to understand if automatic similarity search results are perceived in a similar manner, irrespective of the visualization technique; and if what people perceive as similar with each visualization aligns with different automatic similarity measures and their similarity constraints. Our findings indicate that Horizon Graphs promote as invariant local variations in temporal position or speed, and as a result they align with measures that allow variations in temporal shifting or scaling (i.e., dynamic time warping). On the other hand, Horizon Graphs do not align with measures that allow amplitude and y-offset variations (i.e., measures based on z-normalization), because they exaggerate these differences, while the inverse seems to be the case for Line Charts and Color Fields. Overall, our work indicates that the choice of visualization affects what temporal patterns humans consider as similar, i.e., the notion of similarity in time series is visualization-dependent.In the second part of the thesis, we focused on progressive similarity search in large data series collections. We investigated how fast first approximate and then updates of progressive answers are detected, while we execute similarity search queries. Our findings indicate that there is a gap between the time the final answer is found and the time when the search algorithm terminates, resulting in inflated waiting times without any improvement. Computing probabilistic estimates of the final answer could help users decide when to stop the search process. We developed and experimentally evaluated using benchmarks, a new probabilistic learning-based method that computes quality guarantees (error bounds) for progressive k-Nearest Neighbour (k-NN) similarity search results. Our approach learns from a set of queries and builds prediction models based on two observations: (i) similar queries have similar answers; and (ii) progressive best-so-far (bsf) answers returned by the state-of-the-art data series indexes are good predictors of the final k-NN answer. We provide both initial and incrementally improved estimates of the final answer.

Le mandat consiste à développer un outil afin de détecter les désordres alimentaires chez le porc, dans le but de prévenir des problèmes de croissance ou de maladie potentiels. L'outil proposé analyse les données récoltées sur 5 jours consécutifs (période mémoire) pour prédire la consommation de la journée suivante. Il utilise une régression polynomiale généralisée avec contraintes et lissage. L'outil calcule ensuite la différence entre la prédiction et les observations.

Ce travail de thèse porte sur une variable océanographique importante dans le suivi du climat : la température de surface des océans. Au niveau global, les observations de cette température sont fournies principalement par des radiomètres embarqués sur des satellites. Afin de traiter ce flux important de données, un traitement statistique s'impose dans le but de synthétiser l'information en des cartes globales et quotidiennes de notre variable d'intérêt. Pour ce faire, nous proposons un modèle linéaire de type espace-d'état avec des erreurs Gaussiennes. Nous commençons par présenter ce modèle sur des données issues de séries temporelles ayant un échantillonnage irrégulier. Suit un travail d'inférence avec la mise en place d'un schéma d'estimation des paramètres, basé sur la combinaison d'une méthode des moments et du maximum de vraisemblance au travers de l'algorithme EM et des probabilités de filtrage et lissage de Kalman. Nous appliquons enfin cette méthodologie pour estimer les variances d'erreurs et le paramètre de corrélation temporelle à tout l'océan Atlantique. Nous ajoutons ensuite la composante spatiale et proposons une structure d'ordre deux, séparable, basée sur le produit d'une covariance temporelle et d'une covariance spatiale ani- sotrope. Les paramètres de cette dernière sont estimés sur l'océan Atlantique à partir de techniques géostatistiques usuelles et forment un atlas pertinent pour les océanographes. Fi- nalement, nous montrons que l'apport de l'information spatiale augmente le pouvoir prédictif du modèle.