Notre progiciel PoweR vise à faciliter l'obtention ou la vérification des études empiriques de puissance pour les tests d'ajustement. En tant que tel, il peut être considéré comme un outil de calcul de recherche reproductible, car il devient très facile à reproduire (ou détecter les erreurs) des résultats de simulation déjà publiés dans la littérature. En utilisant notre progiciel, il devient facile de concevoir de nouvelles études de simulation. Les valeurs critiques et puissances de nombreuses statistiques de tests sous une grande variété de distributions alternatives sont obtenues très rapidement et avec précision en utilisant un C/C++ et R environnement. On peut même compter sur le progiciel snow de R pour le calcul parallèle, en utilisant un processeur multicœur. Les résultats peuvent être affichés en utilisant des tables latex ou des graphiques spécialisés, qui peuvent être incorporés directement dans vos publications. Ce document donne un aperçu des principaux objectifs et les principes de conception ainsi que les stratégies d'adaptation et d'extension. / Package PoweR aims at facilitating the obtainment or verification of empirical power studies for goodness-of-fit tests. As such, it can be seen as a reproducible research computational tool because it becomes very easy to reproduce (or detect errors in) simulation results already published in the literature. Using our package, it becomes easy to design new simulation studies. The empirical levels and powers for many statistical test statistics under a wide variety of alternative distributions are obtained fastly and accurately using a C/C++ and R environment. One can even rely on package snow to parallelize their computations, using a multicore processor. The results can be displayed using LaTeX tables or specialized graphs, which can be directly incorporated into your publications. This paper gives an overview of the main design aims and principles as well as strategies for adaptation and extension. Hand-on illustrations are presented to get new users started easily.

Šiame darbe įrodinėju tezę: Berlino dviejų laisvių perskyra pagrįsta, nes tiek praeities, tiek dabarties mąstytojų teorinei minčiai būdingi pozityviosios arba negatyviosios laisvės bruožai. I-oje dalyje pateikiu Berlino pagrindinius dviejų laisvių bruožus. Taip pat nagrinėju Berlino darbus, skirtus lygybės, istorijos filosofijos, pliuralizmo bei Apšvietos ir Romantizmo problematikai. Teigiu, jog Berlinas – negatyviosios laisvės gynėjas, mat jo filosofijoje ginama individo pasirinkimo laisvė, asmuo suprantamas kaip autonomiškas subjektas. Berlinas pasisako už vertybinio pliuralizmo idėjas, teigia, jog visiems žmonėms turi būti garantuotos vienodos galimybės. II-oje dalyje nagrinėju 3-jų žymių praeities mąstytojų laisvės sampratas, įrodinėju, jog jos turi negatyviosios arba pozityviosios laisvės bruožų. Nustatau, kad Loko teorijoje vyrauja negatyviosios laisvės nuostatos, mat autorius teigia, jog visi individai laisvi ir patys gali rinktis gyvenimo tikslus. Spinozos darbus priskiriu pozityviosios laisvės tradicijai, nes autorius teigia, jog laisvi tegali būti individai, besivadovaujantys protu. Teigiu, jog Hegelio sistema priklauso toms pozityviosios laisvės teorijoms, anot kurių asmuo gali būti laisvas tik priklausydamas politinei bendruomenei. III-oje dalyje analizuoju Berlino laisvių perskyros kritiką. Ji pateikiama XX a. Politinių teorijų kontekste: XXa. Vyksta atkaklus ginčas tarp negatyviosios (individualistų) ir pozityviosios (bendruomenininkų) laisvės atstovų. Teigiu... [toliau žr. visą tekstą] / In this work I'm proving thesis: the Berlin's distinction between two freedoms is legitimate, because the attributes of positive or negative freedom are characteristic to the past thinkers' theoretical thought. In the first part I'm setting forth the main characteristics of Berlin's two freedoms. I'm also investingating the works of Berlin, which are investigating the problems of equality, philosophy of history, pluralism and Romanticism and Enlightenment. I maintain that Berlin is proponent of negative freedom, because the freedom of individual choice is protected in his philosophy, person is comprehended as autonomous subject. Berlin is proponent of value pluralism, he maintains that equal opportunities must be ensured for all. In the second part I'm analysing the concepts of freedom of three past thinkers, I'm arguing that these concepts of freedom have the features of negative or positive freedom. I'm settling that there are certain attitudes of negative freedom which are dominating in the theory of Locke: it is because author states that all individuals are free and can freely choose the ends of life. I attribute the works of Spinoza to the tradition of positive freedom, because author states that only mind following people can be free. I state, that the system of Hegel belongs to those theories of positive freedom, according to which person can only be free if he belongs to the political community. In the third part I'm analysing the criticism to the Berlin's freedom... [to full text]

This thesis addresses statistical estimation and testing of signals over a graph when measurements are noisy and high-dimensional. Graph structured patterns appear in applications as diverse as sensor networks, virology in human networks, congestion in internet routers, and advertising in social networks. We will develop asymptotic guarantees of the performance of statistical estimators and tests, by stating conditions for consistency by properties of the graph (e.g. graph spectra). The goal of this thesis is to demonstrate theoretically that by exploiting the graph structure one can achieve statistical consistency in extremely noisy conditions. We begin with the study of a projection estimator called Laplacian eigenmaps, and find that eigenvalue concentration plays a central role in the ability to estimate graph structured patterns. We continue with the study of the edge lasso, a least squares procedure with total variation penalty, and determine combinatorial conditions under which changepoints (edges across which the underlying signal changes) on the graph are recovered. We will shift focus to testing for anomalous activations in the graph, using the scan statistic relaxations, the spectral scan statistic and the graph ellipsoid scan statistic. We will also show how one can form a decomposition of the graph from a spanning tree which will lead to a test for activity in the graph. This will lead to the construction of a spanning tree wavelet basis, which can be used to localize activations on the graph.

Generalized linear mixture models (GLMM) are widely used in statistical applications to model count and binary data. We consider the problem of nonparametric likelihood estimation of mixing distributions in GLMM's with multiple random effects. The log-likelihood to be maximized has the general form l(G)=Σi log∫f(yi,γ) dG(γ) where f(.,γ) is a parametric family of component densities, yi is the ith observed response dependent variable, and G is a mixing distribution function of the random effects vector γ defined on Ω. The literature presents many algorithms for maximum likelihood estimation (MLE) of G in the univariate random effect case such as the EM algorithm (Laird, 1978), the intra-simplex direction method, ISDM (Lesperance and Kalbfleish, 1992), and vertex exchange method, VEM (Bohning, 1985). In this dissertation, the constrained Newton method (CNM) in Wang (2007), which fits GLMM's with random intercepts only, is extended to fit clustered datasets with multiple random effects. Owing to the general equivalence theorem from the geometry of mixture likelihoods (see Lindsay, 1995), many NPMLE algorithms including CNM and ISDM maximize the directional derivative of the log-likelihood to add potential support points to the mixing distribution G. Our method, Direct Search Directional Derivative (DSDD), uses a directional search method to find local maxima of the multi-dimensional directional derivative function. The DSDD's performance is investigated in GLMM where f is a Bernoulli or Poisson distribution function. The algorithm is also extended to cover GLMM's with zero-inflated data. Goodness-of-fit (GOF) and selection methods for mixed models have been developed in the literature, however their application in models with nonparametric random effects distributions is vague and ad-hoc. Some popular measures such as the Deviance Information Criteria (DIC), conditional Akaike Information Criteria (cAIC) and R2 statistics are potentially useful in this context. Additionally, some cross-validation goodness-of-fit methods popular in Bayesian applications, such as the conditional predictive ordinate (CPO) and numerical posterior predictive checks, can be applied with some minor modifications to suit the non-Bayesian approach. / Graduate / 0463 / rabihsaab@gmail.com

Benford’s Law states that the first significant digit for most data is not uniformly distributed. Instead, it follows the distribution: P(d = d1) = log10(1 + 1/d1) for d1 ϵ {1, 2, …, 9}. In 2006, my supervisor, Dr. Mary Lesperance et. al tested the goodness-of-fit of data to Benford’s Law using the first significant digit. Here we extended the research to the first two significant digits by performing several statistical tests – LR-multinomial, LR-decreasing, LR-generalized Benford, LR-Rodriguez, Cramѐr-von Mises Wd2, Ud2, and Ad2 and Pearson’s χ2; and six simultaneous confidence intervals – Quesenberry, Goodman, Bailey Angular, Bailey Square, Fitzpatrick and Sison. When testing compliance with Benford’s Law, we found that the test statistics LR-generalized Benford, Wd2 and Ad2 performed well for Generalized Benford distribution, Uniform/Benford mixture distribution and Hill/Benford mixture distribution while Pearson’s χ2 and LR-multinomial statistics are more appropriate for the contaminated additive/multiplicative distribution. With respect to simultaneous confidence intervals, we recommend Goodman and Sison to detect deviation from Benford’s Law.

Generalized linear mixture models (GLMM) are widely used in statistical applications to model count and binary data. We consider the problem of nonparametric likelihood estimation of mixing distributions in GLMM's with multiple random effects. The log-likelihood to be maximized has the general form l(G)=Σi log∫f(yi,γ) dG(γ) where f(.,γ) is a parametric family of component densities, yi is the ith observed response dependent variable, and G is a mixing distribution function of the random effects vector γ defined on Ω. The literature presents many algorithms for maximum likelihood estimation (MLE) of G in the univariate random effect case such as the EM algorithm (Laird, 1978), the intra-simplex direction method, ISDM (Lesperance and Kalbfleish, 1992), and vertex exchange method, VEM (Bohning, 1985). In this dissertation, the constrained Newton method (CNM) in Wang (2007), which fits GLMM's with random intercepts only, is extended to fit clustered datasets with multiple random effects. Owing to the general equivalence theorem from the geometry of mixture likelihoods (see Lindsay, 1995), many NPMLE algorithms including CNM and ISDM maximize the directional derivative of the log-likelihood to add potential support points to the mixing distribution G. Our method, Direct Search Directional Derivative (DSDD), uses a directional search method to find local maxima of the multi-dimensional directional derivative function. The DSDD's performance is investigated in GLMM where f is a Bernoulli or Poisson distribution function. The algorithm is also extended to cover GLMM's with zero-inflated data. Goodness-of-fit (GOF) and selection methods for mixed models have been developed in the literature, however their application in models with nonparametric random effects distributions is vague and ad-hoc. Some popular measures such as the Deviance Information Criteria (DIC), conditional Akaike Information Criteria (cAIC) and R2 statistics are potentially useful in this context. Additionally, some cross-validation goodness-of-fit methods popular in Bayesian applications, such as the conditional predictive ordinate (CPO) and numerical posterior predictive checks, can be applied with some minor modifications to suit the non-Bayesian approach. / Graduate / 0463 / rabihsaab@gmail.com

Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-08-02T21:21:48Z No. of bitstreams: 1 ALINE BARBOSA TSUYUGUCHI - DISSERTAÇÃO PPGMAT 2012..pdf: 613833 bytes, checksum: c354cd90842e461c0fb29b0ee5f925d3 (MD5) / Made available in DSpace on 2018-08-02T21:21:48Z (GMT). No. of bitstreams: 1 ALINE BARBOSA TSUYUGUCHI - DISSERTAÇÃO PPGMAT 2012..pdf: 613833 bytes, checksum: c354cd90842e461c0fb29b0ee5f925d3 (MD5) Previous issue date: 2012-02 / CNPq / Neste trabalho estudamos testes de bondade de ajuste para a distribuição Birnbaum-Saunders. Consideramos testes clássicos baseados em função de distribuição empírica (Anderson-Darling, Cramér-von Mises e Kolmogorov-Sminorv) e baseados em função característica empírica. Nos limitamos ao caso onde o vetor de parâmetros é desconhecido e, portanto deverá ser estimado. Apresentamos estudos de simulação para verificar o desempenho das estatísticas de teste em estudo. Além disso, propomos estudos de simulação de Monte Carlo para testes de bondade de ajuste para a distribuição Birnbaum-Saunders com dados com censura tipo II. / In this work we study goodness-of-fit tests for Birnbaum-Saunders distribution. We consider classical tests based on empirical distribution function (Anderson-Darling, Cramér-von Mises e Kolmogorov-Sminorv) and based on empirical characteristic function. We limited this study to the case in which the vector of parameters is unknown and, therefore, must be estimated. We present the simulation studies to verify the performance of the test statistics in study. Also, we propose simulation studies of Monte Carlo for goodness-of-fit test for Birnbaum-Saunders distribution using Type-II censored data.

From the knowledge gained by studying scientific publications and other resources on possibilities of applying stochastic approach in planning, directing and controlling the projects will be evaluated time analysis of the construction project. The project will be analyzed using simulation techniques. The subject of research, the project Modernization of the Czech Budejovice - Nemanice, which will be designed for appropriate recommendations.

This work deals with the comparison of Plato and Aristotle's conception of virtue ethics. The first part describes Plato's view of this area of philosophy. Plato puts his ethics based on the analogy between the municipality and the soul. Plato also operates with good ideas. In the second part, Aristotle view. First, I discuss the objectives of its philosophy, which is good, and then bliss. Then there is the division of the moral virtues and intellectual. Then describe each of Aristotle's virtues. The third main section consists of two subsections, the first of which generally compare both concepts when I find the first differences in the overall approach of both authors. In the second subsection I compare other points of doctrine, especially community, friendship and goodness.

Submitted by Viviane Lima da Cunha (viviane@biblioteca.ufpb.br) on 2017-06-26T11:50:59Z No. of bitstreams: 1 arquivototal.pdf: 7515806 bytes, checksum: a09d41d012f6b4bd6ac4e7f7ffd37975 (MD5) / Made available in DSpace on 2017-06-26T11:50:59Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 7515806 bytes, checksum: a09d41d012f6b4bd6ac4e7f7ffd37975 (MD5) Previous issue date: 2017-03-22 / Many indicators have been used to verify the e ciency and quality of services in primary health care. Recently, this level of attention has been evaluated in Brazil. The ambulatory cary sensitive conditions (ACSC), represent a set of health problems that should not reach tertiary care in large numbers, since an e ective primary care action would solve some of these pathologies. Hear, the present study is justi ed by the need to use hospitalizations for ACSC as a base for quality and access indicator for the Primary Care of the health system of Brazilian cities, in association with the Family Health Strategy (FHS). Therefore, we aim to estimate statistical reference values for ambulatory cary sensitive conditions, based on the adjustment of continuous probability distributions, in order to classify the health system of the Brazilian cities into levels of performance, namely: desirable, intermediate, worrying and not acceptable. The thesis that is defended is that the achievement of a statistical reference value, capable of classifying by ASCS, in performance levels for the Brazilian cities, will aid in decision-making processes in the units of FHS, optimizing the health actions in these units, as well as, providing the prevention of unnecessary expenses in the other levels of attention. This is an epidemiological, ecological and inferential study of quantitative approaches, based on the secondary database of the Hospital Information System of the Unique Health System, with the selection of absolute frequencies of diagnostic groups referring to ambulatory cary sensitive conditions to Primary Care, for 2015. Subsequently, these frequencies were transformed into rates per 10,000 inhabitants, making it possible to compare the ACSCs of all Brazilian cities, regardless of their population contingents. From the statistical point of view, the adjustment of continuous probability distributions through the goodness-of- t tests and graphic support were processed using software R, version 3.0.3. Based on the results, a greater incidence of hospital admissions was observed due to pathologies related to gastroenteric, cardiac and renal problems. In view of the three scenarios investigated (Brazil, Northeast and Para ba), the Northeast presents records of hospitalizations for asthma, a diagnosis not observed as one of the three highest incidences at national and state level. It was also evidenced that most of the Brazilian cities investigated in this study have their health systems classi ed as not acceptable. The city of S~ao Paulo, for example, is one such case accounting for 9.471 hospitalizations of patients with heart failure in 2015. Thus, its health system would be considered desirable if there were up to 1.532 records. An intermediate level of performance would range from more than 1.532 to a maximum of 2.944 cases, while the level of concern would be more than 2.944 to 4.177 hospitalizations. An unacceptable performance level is recorded from 4.177 ICSAP. In Brazil, when it comes to the Basic Attention scenario, although advances are perceived, the prospect of reducing the ACSC to minimum values, as is desirable, is still far from the reality. The use of the statistical reference value may constitute a potential tool, ready to use of the administrative managers in order to direct and subsidize proposals of health actions in the cities under their responsibility. / Uma variedade de indicadores tem sido utilizada para averiguar a e ciência e a qualidade de serviços na atenção primaria a saúde. Nos últimos anos, esse nível de atenção vem passando por avaliações no Brasil. As internações por condições sensíveis a atenção primária (ICSAP), representam um conjunto de agravos de saúde que não deveriam chegar em grande quantidade a atenção terciária, posto que uma efetiva ação da atenção primária solucionaria parte dessas patologias. Nesse contexto, a presente pesquisa se justiça pela necessidade de utilizar as ICSAP como base para um indicador de acesso e de qualidade da Atenção básica do sistema de saúde dos municípios brasileiros, em associação com a Estratégia Saúde da Família (ESF). Portanto, objetiva-se estimar valores estatísticos de referência para as internações por condições sensíveis a atenção primária, a partir do ajuste de distribuições de probabilidade contínuas, de modo a classificar o sistema de saúde dos municípios brasileiros em níveis de desempenho, a saber: desejável, intermediário, preocupante e não aceitável. Defende-se a tese de que a obtenção de um valor estatístico de referência, capaz de classificar as ICSAP, em níveis de desempenho para os municípios brasileiros, auxiliará nos processos de tomadas de decisão nas unidades de ESF, otimizando as ações de saúde nessas unidades, bem como, proporcionando a prevenção de gastos desnecessários nos outros níveis de atenção. Trata-se de um estudo epidemiológico, ecológico e inferencial, de abordagem quantitativa, realizado a partir da base de dados secundários do Sistema de Informações Hospitalares do SUS com a seleção das freqüências absolutas dos grupos de diagnósticos referentes as internações por condições sensíveis à atenção primária, referentes ao ano de 2015. A posteriori, as referidas freqüências foram transformadas em taxas por 10.000 habitantes possibilitando a comparação das ICSAP de todos os municípios brasileiros, independente dos seus contingentes populacionais. Sob o ponto de vista estatístico, o ajuste de distribuições de probabilidade contínuas por meio dos testes de aderência e suporte gráfico foram processados utilizando o software R 3.0.3. Com base nos resultados, observou-se uma incidência maior de internações hospitalares devido _a patologias relacionadas a problemas gastroentéricos, cardíacos e renais. Diante dos três cenários investigados (Brasil, Nordeste e Paraíba), a região Nordeste apresenta registros de internações por asma, diagnóstico não observado como uma das três maiores incidências a nível nacional e estadual. Evidenciou-se também, que a maioria dos municípios brasileiros investigados nesse estudo têm seus sistemas de saúde classificados como não aceitáveis. A cidade de São Paulo, por exemplo, é um desses casos, contabilizando 9.471 internações de pacientes com insuficiência cardíaca em 2015. Assim, seu sistema de saúde seria considerado de nível desejável se houvessem até 1.532 registros. Um nível intermediário de desempenho seria de mais de 1.532 até no máximo 2.944 casos, enquanto que, o nível preocupante dar-se-_a com mais de 2.944 até 4.177 internações. Um nível de desempenho não aceitável é registrado a partir de 4.177 ICSAP. No Brasil, em se tratando do quadro de Atenção Básica, embora avanços sejam percebidos, a perspectiva de redução das ICSAP a valores mínimos, como é desejável, ainda está distante da realidade. A utilização do valor estatístico de referência poder á constituir-se de uma potencial ferramenta, a disposição dos gestores administrativos no intuito de direcionar e subsidiar propostas de ações de saúde nos municípios sob sua responsabilidade.