Uma questão interessante na política monetária é se os Bancos Centrais dão pesos iguais para desvios positivos e negativos da inflação e do hiato do produto das suas respectivas metas. Para responder à esta questão, estimou-se a função perda da autoridade monetária não parametricamente através do método de sieve estimator, expandindo-a através de uma base composta de polinômios ortogonais. A economia foi modelada com agentes foward-looking e com comprometimento por parte da autoridade monetária. O método foi aplicado para a os Estados Unidos desde 1960 e para o Brasil a partir de 1999. Para a economia norte-americana não foram encontradas evidências de assimetria nas preferências da autoridade monetária. Já no Brasil o Banco Central mostrou ter preferências assimétricas quanto à inflação, auferindo uma maior perda de desvios negativos do que positivos em relação à meta. / An interesting question in monetary policy is whether the Central Bank gives equal weights to positive and negative deviations of inflation and output gap from their targets. Trying answering this question, we estimated the monetary authority’s loss function nonparametrically, using the method of sieves, expanding it with orthogonal polynomials. The economy was model with forward-looking agents and with commitment of the monetary authority. We applied the method to U.S. monetary policy since 1960 and for Brazil since 1999. For the U.S. economy, it was not found evidence of asymmetry in the preferences of the monetary authority. In Brazil, the Central Bank proved to have asymmetric preferences about inflation, with a greater loss for negative deviations of inflation from the target rather for positive ones.

Submitted by Aline Batista (alinehb.ufpel@gmail.com) on 2018-06-18T19:43:10Z No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Dissertacao_Mauricio_Fornalski.pdf: 2690628 bytes, checksum: e2befdb01ae8864fb80bc95757c1f588 (MD5) / Approved for entry into archive by Aline Batista (alinehb.ufpel@gmail.com) on 2018-06-18T19:47:40Z (GMT) No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Dissertacao_Mauricio_Fornalski.pdf: 2690628 bytes, checksum: e2befdb01ae8864fb80bc95757c1f588 (MD5) / Made available in DSpace on 2018-06-18T19:47:47Z (GMT). No. of bitstreams: 2 license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Dissertacao_Mauricio_Fornalski.pdf: 2690628 bytes, checksum: e2befdb01ae8864fb80bc95757c1f588 (MD5) Previous issue date: 2018-02-06 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / A demanda da população por água é reconhecidamente um fator ligado a qualidade de vida e pode ser um indicativo de desenvolvimento econômico e social de uma determinada região. O Brasil, a exemplo de outros países em desenvolvimento, apresenta escassez em informações ligadas aos recursos hídricos, embora possua um vasto potencial hidrológico na maior parte do seu território. Neste contexto, a compreensão da dinâmica da água no solo é fundamental no estudo de bacias hidrográficas destacando-se principalmente pela influência em variáveis hidrológicas e hidrossedimentológicas. O monitoramento da umidade do solo em bacias hidrográficas apresenta alta complexidade devido principalmente a sua variabilidade espacial e temporal. Os atributos físico-hídricos fornecem informações importantes para diversas áreas do conhecimento como a estimativa da suscetibilidade do solo à erosão, modelagem hidrológica, projetos de irrigação, etc. Este trabalho teve como objetivo caracterizar nove atributos físico-hídricos e o carbono orgânico do solo visando avaliar a variabilidade espacial inerente à heterogeneidade fisiográfica da paisagem em uma bacia hidrográfica e validar a hipótese intrínseca da geoestatística. O estudo foi conduzido em uma sub-bacia hidrográfica do Arroio Pelotas denominada de Bacia Hidrográfica da Sanga Ellert (BHSE), localizada no município de Canguçu. A bacia possui área de aproximadamente 70ha e a altitude varia de 310,9 a 419,4 metros. As áreas estudadas compreendem basicamente uma classe de solos, os Neossolos. A estatística descritiva e a geoestatística foram utilizadas para se determinar a magnitude e a variabilidade espacial do carbono orgânico e dos seguintes atributos físico-hídricos do solo: Areia, argila, densidade do solo, porosidade total, macroporosidade, microporosidade, capacidade de campo, ponto de murcha permanente e condutividade hidráulica do solo saturado . A análise exploratória dos dados demonstrou ausência de normalidade para a maior parte das variáveis, exceto para o teor de areia, microporosidade e umidade na capacidade de campo. No campo da estatística clássica ainda podemos salientar correlações esperadas para estes atributos demonstradas pela matriz Correlação de Pearson, como para o teor de areia e a capacidade de campo; teor de argila e ponto de murcha permanente; Condutividade hidráulica do solo saturado com a densidade do solo e macroporosidade; e a microporosidade com a capacidade de campo. Para todos os atributos que apresentaram séries não normais foi empregado o estimador robusto de Cressie e Hawkins para a construção dos semivariogramas bem como para os atributos areia e capacidade de campo, que apresentaram outliers em suas séries de dados. Apenas para o atributo microporosidade foi empregado o estimador clássico de Matheron. Os resultados demonstraram que, exceto para os atributos físico-hídricos areia e argila, os demais atributos avaliados no presente trabalho demonstraram continuidade espacial e que a partir da malha amostral proposta foi possível identificar esta condição, bem com realizar a interpolação dos dados empregando a técnica da krigagem ordinária. / The population's demand for water is admittedly a factor linked to the quality of life and can be indicative of the economic and social development of a given region. Brazil, like other developing countries, has a shortage of information related to water resources, although it has a vast hydrological potential in most of its territory. In this context, the understanding of soil water dynamics is fundamental in the study of hydrographic basins, emphasizing mainly the influence on hydrological and hydrosedimentological variables. The monitoring of soil moisture in watersheds presents high complexity due mainly to its spatial and temporal variability. Soil hydro-physical attributes provide important information for several areas of knowledge, such as the estimation of soil susceptibility to erosion, hydrological modeling, irrigation projects, etc. The objective of this work was to characterize ten soil hydro-physical attributes in order to evaluate the spatial variability inherent to the physiographic heterogeneity of the landscape in a hydrographic basin and to validate the intrinsic hypothesis of geostatistics. The study was conducted in a sub-basin of Arroio Pelotas called the Sanga Ellert Basin (BHSE), located in the municipality of Canguçu. The basin has an area of approximately 70ha and the altitude varies from 310.9 to 419.4 meters. The studied areas basically comprise a class of soils, the Neosols. Descriptive statistics and geostatistics were used to determine the magnitude and spatial variability of the following soil physical-water attributes: Sand, clay, soil density, total porosity, macroporosity, microporosity, field capacity, permanent wilting point and saturated soil hydraulic conductivity and also to soil organic carbon,. The exploratory analysis of the data showed non-normality for most of the variables, except for the sand content, microporosity and field capacity. Falling on of classical statistics we can still emphasize expected correlations for these attributes demonstrated by the Pearson coefficient, as for the sand content and the field capacity; clay content and permanent wilting point; saturated soil hydraulic conductivity with soil density and macroporosity; and microporosity with field capacity. For all the attributes that presented non-normal series, the robust estimator of Cressie and Hawkins was used for the construction of semivariograms as well as for the attributes sand and field capacity, which presented outliers in their data. Only for the microporosity the Matheron's classical estimator has been used. The results showed that, except for the hydro-physical attributes sand and clay content, the other attributes evaluated in the present study demonstrated spatial continuity and that from the proposed sampling grid is possible to identify this condition, as well as to perform the data interpolation using the ordinary kriging technique.

Neste trabalho são apresentadas estratégias para a estimação, em processos químicos, de estados, parâmetros e covariâncias do ruído de processo e das medidas que são testadas com dados experimentais. Para a estimação de estados e parâmetros foram implementadas desde a técnica mais tradicional, o filtro estendido de Kalman (EKF) até as mais modernas da literatura, como o filtro de Kalman Unscented (UKF) e o Moving Horizon Estimator (MHE). A técnica Autocovariance Least-Squares (ALS) permite a estimação das matrizes de covariância do processo e das medidas a partir dos estados medidos dos processos analisados. Três processos foram analisados com as técnicas citadas: a reação de hidrólise de anidrido acético, o aquecimento de um reator de polimerização completamente carregado (sem iniciador) e por fim oito reações diferentes de polimerização em emulsão. Os resultados mostraram que uma sintonia por tentativa e erro para as matrizes de covariância não apresenta um desempenho adequado. Adicionalmente, o UKF mostra um melhor desempenho, quando comparado com o EKF para o monitoramento de processos de polimerização regime em batelada com covariâncias obtidas através de otimização direta. Quando a estimação da covariância com a técnica ALS é implementada e os resultados utilizados em estimadores estocásticos, o desempenho dos estimadores recursivos melhora consideravelmente. Além disso, o MHE mostrou ser uma ferramenta robusta para o monitoramento do coeficiente global de troca térmica (UA) e do calor gerado pela reação para a polimerização em emulsão em regime semi-contínuo. Finalmente, duas características vantajosas da metodologia proposta devem ser destacadas: a independência em relação ao valor inicial para o estado UA e o fato de um único conjunto de matrizes de covariância (quando obtida pela técnica ALS) poder ser utilizado em reações diferentes, sem necessidade de sintonizar novamente as matrizes para cada reação. / In this work, strategies for state, parameter and covariance estimation in chemical processes are presented and tested with experimental data. For state and parameter estimation techniques have been implemented that spread from the traditional Extended Kalman Filter (EKF) to the most modern techniques from literature, such as the Unscented Kalman Filter (UKF) and the Moving Horizon Estimator (MHE). The Autocovariance Least-Squares technique (ALS) allows the covariance matrices of the process and measurement noise to be estimated based on the measured states of the processes analyzed. Three cases were studied using these techniques: the hydrolysis of acetic anhydride, the warming-up stage of a fully charged polymerization reactor (without initiator) to the desired temperature and finally, eight different emulsion polymerization reaction runs. Results showed that determining covariance matrices by trial and error does not lead to an adequate performance. Additionally, the UKF presents a better performance than the EKF for batch polymerization processes with covariance matrices obtained by direct optimization. When the estimation of the covariance is performed by the ALS technique and they are used in a stochastic estimator, the performance of the recursive estimators is considerably improved. Furthermore, the MHE proved to be a robust tool for monitoring the overall heat transfer coefficient (UA) and the heat of reaction for fedbatch emulsion polymerization. Finally, two positive features of the proposed methodology must be highlighted, its low dependency on the initial state condition of UA and the fact that a unique set of covariance matrices (when obtained by the ALS technique) can be used for different reaction runs, without the necessity of tuning the matrices again for each reaction.

Este trabalho é dedicado ao estudo do erro de estimação em filtragem linear para sistemas lineares com parâmentros sujeitos a saltos markovianos a tempo discreto. Indroduzimos o conceito de alcançabilidade média para uma classe de sistemas. Construímos um conjunto de matrizes de alcançabilidade e mostramos que o conceito usual de alcan- çabilidade definido através da positividade do gramiano é caracterizado pela definição por posto completo destas matrizes. A alcançabilidade média funciona como condição necessária e suficiente para positividade do segundo momento do estado do sistema, resultado esse que auxilia na caracterização da positividade uniforme da matriz de covariância do erro de estimação. Abordamos a estabilidade de estimadores com a interpretação de que a covariância do erro permanece limitada na presença de erro de qualquer magnitude no modelo do ruído, que é uma característica relevante para aplicações. Apresentamos uma prova de que filtros markovianos são estáveis sempre que o segundo momento condicionado é positivo. Exemplos numéricos encontram-se inclusos. / This work studies linear filtering for discrete-time systems with Markov jump parameters. We introduce a notion of average reachability for these systems and present a set of matrices playing the role of reachability matrices, in the sense that their rank is full if and only if the system is average reachable. Reachability is also a sufficient condition for the second moment of the system to be positive. Uniform positiveness of the error covariance matrix is studied for general (possibly non-markovian) linear estimators, relying on the state second moment positiveness. Satbility of linear markovian estimators is also addressed, allowing to show that markovian estimators are stable whenever the system is reachable, with the interpretation that the error covariance remains bounded in the presence of error of any magnitude in the model of the noise, which is a relevant feature for applications. Numerical examples are included.

Au cours des dernières années, des changements importants dans le domaine des assurances et des finances attirent de plus en plus l’attention sur la nécessité d’élaborer un cadre normalisé pour la mesure des risques. Récemment, il y a eu un intérêt croissant de la part des experts en assurance sur l’utilisation de l’espérance conditionnelle des pertes (CTE) parce qu’elle partage des propriétés considérées comme souhaitables et applicables dans diverses situations. En particulier, il répond aux exigences d’une mesure de risque “cohérente”, selon Artzner [2]. Cette thèse représente des contributions à l’inférence statistique en développant des outils, basés sur la convergence des intégrales fonctionnelles, pour l’estimation de la CTE qui présentent un intérêt considérable pour la science actuarielle. Tout d’abord, nous développons un outil permettant l’estimation de la moyenne conditionnelle E[X|X > x], ensuite nous construisons des estimateurs de la CTE, développons la théorie asymptotique nécessaire pour ces estimateurs, puis utilisons la théorie pour construire des intervalles de confiance. Pour la première fois, l’approche de bootstrap non paramétrique est explorée dans cette thèse en développant des nouveaux résultats applicables à la valeur à risque (VaR) et à la CTE. Des études de simulation illustrent la performance de la technique de bootstrap.

La tomodensitométrie est une technique très utile qui permet de mener avec succès des analyses non-invasives dans plusieurs types d'applications, par exemple médicales ou industrielles. L'analyse manuelle des structures d'intérêt présentes dans une image peut prendre beaucoup de temps, être laborieuse et parfois même impossible à faire en raison de sa complexité. C'est pour cela que dans cette thèse, nous proposons et développons des algorithmes nécessaires à cette analyse, basés sur la géométrie discrète et la topologie. Ces algorithmes peuvent servir dans de nombreuses applications, et en particulier au niveau de l'analyse quantitative automatique de l'arbre bronchique humain, sur la base d'images de tomodensitométrie. La première partie introduit les notions fondamentales de la topologie et de la géométrie discrètes utiles dans cette thèse. Ensuite, nous présentons le principe de méthodes utilisées dans de nombreuses applications : les algorithmes de squelettisation, de calcul de l'axe médian, les algorithmes de fermeture de tunnels et les estimateurs de tangentes. La deuxième partie présente les nouvelles méthodes que nous proposons et qui permettent de résoudre des problèmes particuliers. Nous avons introduit deux méthodes nouvelles de filtrage d'axe médian. La première, que nous appelons "hierarchical scale medial axis", est inspirée du "scale axis transform", sans les inconvénients qui sont propres à la méthode originale. La deuxième est une méthode nommée "discrete adaptive medial axis", où le paramètre de filtrage est adapté dynamiquement aux dimensions locales de l'objet. Dans cette partie, nous introduisons également des estimateurs de tangente nouveaux et efficaces, agissant sur des courbes discrètes tridimensionnelles, et que nous appelons "3Dlambda maximal segment tangent direction". Enfin, nous avons montré que la géométrie discrète et les algorithmes topologiques pouvaient être utiles dans le problème de l'analyse quantitative de l'arbre bronchique humain à partir d'images tomodensitométriques. Dans une chaîne de traitements de structure classique par rapport à l'état de l'art, nous avons appliqué des méthodes de topologie et de géométrie discrète afin de résoudre des problèmes particuliers dans chaque étape du processus de l'analyse quantitative. Nous proposons une méthode robuste pour segmenter l'arbre bronchique à partir d'un ensemble de données tomographiques (CT). La méthode est basée sur un algorithme de fermeture de tunnels qui est utilisé comme outil pour réparer des images CT abîmées par les erreurs d'acquisition. Nous avons aussi proposé un algorithme qui sert à créer un modèle artificiel d'arbre bronchique. Ce modèle est utilisé pour la validation des algorithmes présentés dans cette thèse. Ensuite nous comparons la qualité des différents algorithmes en utilisant un ensemble de test constitué de fantômes (informatiques) et d'un ensemble de données CT réelles. Nous montrons que les méthodes récemment présentées dans le cadre des complexes cubiques, combinées avec les méthodes présentées dans cette thèse, permettent de surmonter des problèmes indiqués par la littérature et peuvent être un bon fondement pour l'implémentation future des systèmes de quantification automatique des particularités de l'arbre bronchique / Computed tomography is a very useful technic which allow non-invasive diagnosis in many applications for example is used with success in industry and medicine. However, manual analysis of the interesting structures can be tedious and extremely time consuming, or even impossible due its complexity. Therefore in this thesis we study and develop discrete geometry and topology algorithms suitable for use in many practical applications, especially, in the problem of automatic quantitative analysis of the human airway trees based on computed tomography images. In the first part, we define basic notions used in discrete topology and geometry then we showed that several class of discrete methods like skeletonisation algorithms, medial axes, tunnels closing algorithms and tangent estimators, are widely used in several different practical application. The second part consist of a proposition and theory of a new methods for solving particular problems. We introduced two new medial axis filtering method. The hierarchical scale medial axis which is based on previously proposed scale axis transform, however, is free of drawbacks introduced in the previously proposed method and the discrete adaptive medial axis where the filtering parameter is dynamically adapted to the local size of the object. In this part we also introduced an efficient and parameter less new tangent estimators along three-dimensional discrete curves, called 3D maximal segment tangent direction. Finally, we showed that discrete geometry and topology algorithms can be useful in the problem of quantitative analysis of the human airway trees based on computed tomography images. According to proposed in the literature design of such system we applied discrete topology and geometry algorithms to solve particular problems at each step of the quantitative analysis process. First, we propose a robust method for segmenting airway tree from CT datasets. The method is based on the tunnel closing algorithm and is used as a tool to repair, damaged by acquisition errors, CT images. We also proposed an algorithm for creation of an artificial model of the bronchial tree and we used such model to validate algorithms presented in this work. Then, we compare the quality of different algorithms using set of experiments conducted on computer phantoms and real CT dataset. We show that recently proposed methods which works in cubical complex framework, together with methods introduced in this work can overcome problems reported in the literature and can be a good basis for the further implementation of the system for automatic quantification of bronchial tree properties

This piece of work deals with a philosophy of design adaptive controller, which is based on knowledge of mathematical model controlled plant. This master thesis is focused on closed-loop on-line parametric identification methods. An estimation of model´s parametres is solved by two main concepts: recursive leastsquare algorithms and neural estimators. In case of least-squares algorithm the strategy of preventing the typical problems are solved here. For instance numerical stability, accurecy and restricted forgetting. Back Propagation and Marquardt- Levenberg algorithm were choosen to represent artificial inteligence. There is still a little supermacy on the side of methods based on least-squares algorithm. To compare individual algorithms the grafical interface in MATLAB/Simulink was created.

Ce document traite du problème de la grande dimension dans des processus GARCH multivariés. L'auteur propose une nouvelle dynamique vine-GARCH pour des processus de corrélation paramétrisés par un graphe non dirigé appelé "vine". Cette approche génère directement des matrices définies-positives et encourage la parcimonie. Après avoir établi des résultats d'existence et d'unicité pour les solutions stationnaires du modèle vine-GARCH, l'auteur analyse les propriétés asymptotiques du modèle. Il propose ensuite un cadre général de M-estimateurs pénalisés pour des processus dépendants et se concentre sur les propriétés asymptotiques de l'estimateur "adaptive Sparse Group Lasso". La grande dimension est traitée en considérant le cas où le nombre de paramètres diverge avec la taille de l'échantillon. Les résultats asymptotiques sont illustrés par des expériences simulées. Enfin dans ce cadre l'auteur propose de générer la sparsité pour des dynamiques de matrices de variance covariance. Pour ce faire, la classe des modèles ARCH multivariés est utilisée et les processus correspondants à celle-ci sont estimés par moindres carrés ordinaires pénalisés. / This document contributes to high-dimensional statistics for multivariate GARCH processes. First, the author proposes a new dynamic called vine-GARCH for correlation processes parameterized by an undirected graph called vine. The proposed approach directly specifies positive definite matrices and fosters parsimony. The author provides results for the existence and uniqueness of stationary solution of the vine-GARCH model and studies its asymptotic properties. He then proposes a general framework for penalized M-estimators with dependent processes and focuses on the asymptotic properties of the adaptive Sparse Group Lasso regularizer. The high-dimensionality setting is studied when considering a diverging number of parameters with the sample size. The asymptotic properties are illustrated through simulation experiments. Finally, the author proposes to foster sparsity for multivariate variance covariance matrix processes within the latter framework. To do so, the multivariate ARCH family is considered and the corresponding parameterizations are estimated thanks to penalized ordinary least square procedures.

No description available.

Nous considérons le problème d’estimation de densités conditionnelles en modérément grandes dimensions. Beaucoup plus informatives que les fonctions de régression, les densités condi- tionnelles sont d’un intérêt majeur dans les méthodes récentes, notamment dans le cadre bayésien (étude de la distribution postérieure, recherche de ses modes...). Après avoir rappelé les problèmes liés à l’estimation en grande dimension dans l’introduction, les deux chapitres suivants développent deux méthodes qui s’attaquent au fléau de la dimension en demandant : d’être efficace computation- nellement grâce à une procédure itérative gloutonne, de détecter les variables pertinentes sous une hypothèse de parcimonie, et converger à vitesse minimax quasi-optimale. Plus précisément, les deux méthodes considèrent des estimateurs à noyau bien adaptés à l’estimation de densités conditionnelles et sélectionnent une fenêtre multivariée ponctuelle en revisitant l’algorithme glouton RODEO (Re- gularisation Of Derivative Expectation Operator). La première méthode ayant des problèmes d’ini- tialisation et des facteurs logarithmiques supplémentaires dans la vitesse de convergence, la seconde méthode résout ces problèmes, tout en ajoutant l’adaptation à la régularité. Dans l’avant-dernier cha- pitre, on traite de la calibration et des performances numériques de ces deux procédures, avant de donner quelques commentaires et perspectives dans le dernier chapitre. / We consider the problem of conditional density estimation in moderately large dimen- sions. Much more informative than regression functions, conditional densities are of main interest in recent methods, particularly in the Bayesian framework (studying the posterior distribution, find- ing its modes...). After recalling the estimation issues in high dimension in the introduction, the two following chapters develop on two methods which address the issues of the curse of dimensionality: being computationally efficient by a greedy iterative procedure, detecting under some suitably defined sparsity conditions the relevant variables, while converging at a quasi-optimal minimax rate. More precisely, the two methods consider kernel estimators well-adapted for conditional density estimation and select a pointwise multivariate bandwidth by revisiting the greedy algorithm RODEO (Regular- isation Of Derivative Expectation Operator). The first method having some initialization problems and extra logarithmic factors in its convergence rate, the second method solves these problems, while adding adaptation to the smoothness. In the penultimate chapter, we discuss the calibration and nu- merical performance of these two procedures, before giving some comments and perspectives in the last chapter.