Master of Science / Department of Statistics / Christopher Vahl / Among the most used statistical concepts and techniques, seen even in the most cursory of introductory courses, are the confidence interval, binomial distribution, and sample size estimation. This paper investigates a particular case of generating a confidence interval from a binomial experiment in the case where zero successes are expected. Several current methods of generating a binomial proportion confidence interval are examined by means of large-scale simulations and compared in order to determine an ad-hoc method for generating a confidence interval with coverage as close as possible to nominal while minimizing width. This is then used to construct a formula which allows for the estimation of a sample size necessary to obtain a sufficiently narrow confidence interval (with some predetermined probability of success) using the ad-hoc method given a prior estimate of the probability of success for a single trial. With this formula, binomial experiments could potentially be planned more efficiently, allowing researchers to plan only for the amount of precision they deem necessary, rather than trying to work with methods of producing confidence intervals that result in inefficient or, at worst, meaningless bounds.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2015-12-10T10:32:17Z No. of bitstreams: 1 ricardoguimaraesdealmeida.pdf: 1238810 bytes, checksum: 7406c5368a23ac5eb633c275c1427013 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2015-12-10T14:04:32Z (GMT) No. of bitstreams: 1 ricardoguimaraesdealmeida.pdf: 1238810 bytes, checksum: 7406c5368a23ac5eb633c275c1427013 (MD5) / Made available in DSpace on 2015-12-10T14:04:32Z (GMT). No. of bitstreams: 1 ricardoguimaraesdealmeida.pdf: 1238810 bytes, checksum: 7406c5368a23ac5eb633c275c1427013 (MD5) Previous issue date: 2015-08-15 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Este estudo tem como objetivo descrever os conceitos de razão e proporção através de situações que estão presentes no cotidiano popular, buscando estabelecer relações da vida prática do leitor com a matemática ensinada nas escolas por análise e resolução de problemas. Os modelos ora apresentados podem ser utilizados por professores e aplicados em salas de aula do ensino fundamental, sendo úteis àqueles que desejam compreender esses conceitos para aplicá-los em situações matemáticas que possam ser resolvidas através do uso dessas importantes ferramentas. Foi desenvolvido um estudo detalhado, aplicado e diversificado das razões, com a finalidade de garantir ao leitor fundamentos sólidos para a compreensão e resolução dos problemas de proporções, conhecidos por Regra de Três e Porcentagem, através de métodos que utilizam análises lógicas de fácil compreensão, inclusive para os não simpatizantes da matemática. / This study has as its objective to describe the concepts of ration and proportion through everyday situations, seeking to establish matches in the reader’s practical life with mathematics taught in schools by analysis and problem solving. The presented models can be used by teachers and applied in classes of elementary school, and also may be useful to those who wish to comprehend the concepts in order to apply them in mathematical situations which can be solved by the use of these important means. We aimed to develop a detailed study, applied and diversified, of the ratios with the objective of guaranteeing to the reader solid fundaments for its comprehension and to solve proportion problems, known as The Rule of Three and Percentage, through methods which use logical analysis of easy comprehension, even for those who are not familiar with mathematics.

Submitted by Rosangela Silva (rosangela.silva3@unioeste.br) on 2017-08-30T20:10:51Z No. of bitstreams: 2 TAISA PEREIRA PIACENTINI RIBEIRO.pdf: 3904493 bytes, checksum: 479855c30863d881e3a40de6b85ca548 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) / Made available in DSpace on 2017-08-30T20:10:51Z (GMT). No. of bitstreams: 2 TAISA PEREIRA PIACENTINI RIBEIRO.pdf: 3904493 bytes, checksum: 479855c30863d881e3a40de6b85ca548 (MD5) license_rdf: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) Previous issue date: 2017-02-09 / The search for new herbicides to control herbicides-resistant weeds is necessary to attend the rising demand of food from the world’s population. This work was divided into two parts. The first aimed to obtain a model of QSAR-2D, 3D and hybrid to predict compounds with activity to the inhibition of photosynthesis. For this, was used a data set of 44 quinoline analogues described in the literature as PET inhibitors, and all tested in the same bioassay method. For construction of models were used the programs QSAR Modeling and Pentacle. The obtained models A, C and D, were approved in the validation tests (internal and external), they are robust and with good predictive capacity. The second part of studie aimed to identify a pharmacophore model, for select compounds from the data set of first part, aiming to use as a tool for virtual screening. The research resulted in 86,560 compounds, and thus several screening filters were applied according to Briggs rule of three, in silico toxicity analyzes, unsupervised pattern recognition (PCA), and docking studies. As a result, 28 compounds remained, all of which showed potential to be herbicides, through the prediction using the obtained QSAR models, however, only the model D proved to be reliable for prediction the virtual screening. Finally, we selected the ten compounds that presented the highest predictive value of PET inhibition activity, using the model D. / A busca de novos herbicidas para o controle de ervas daninhas resistentes é necessária para atender à crescente demanda alimentar da população mundial. Este trabalho foi dividido em duas partes. A primeira teve por objetivo a obtenção de modelos de QSAR-2D, 3D e híbrido para previsão de compostos com atividade de inibição da fotossíntese. Para isso, foi utilizado um conjunto de dados formado por 44 análogos de quinolina descritos na literatura como inibidores do PET e todos testados pela mesma metodologia de ensaio biológico. Para construção dos modelos foram utilizados os programas QSAR Modeling e Pentacle. Os modelos A, C e D obtidos foram aprovados nos testes de validação (interna e externa), são robustos e com boa capacidade de previsão. A segunda parte do estudo teve como objetivo a identificação de um modelo farmacofórico, para compostos selecionados do conjunto de dados da primeira parte, visando o uso do mesmo como ferramenta para triagem virtual. A pesquisa resultou em 86.560 compostos, e assim foram aplicados diversos filtros de seleção de acordo com a regra de três de Briggs, análises “in silico” de toxicidade, técnica de reconhecimento de padrões não supervisionados (PCA), e estudos e ancoramento molecular. Como resultado, restaram 28 compostos, sendo que todos mostraram potencial para serem herbicidas, através da previsão utilizando os modelos de QSAR obtidos, porém apenas o modelo D mostrou-se confiável para previsão da triagem virtual. Por fim, foram selecionados os dez compostos que apresentaram maior valor de previsão de atividade de inibição do PET, utilizando o modelo D.

Submitted by Cássia Santos (cassia.bcufg@gmail.com) on 2015-02-09T11:31:34Z No. of bitstreams: 3 Dissertação - Rogerio Mastrela - 2014.pdf: 2463662 bytes, checksum: db1006c64be351ea8d3925a544571f33 (MD5) Dissertação - Rogerio Mastrela - 2014.pdf: 2463662 bytes, checksum: db1006c64be351ea8d3925a544571f33 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2015-02-20T10:48:22Z (GMT) No. of bitstreams: 3 Dissertação - Rogerio Mastrela - 2014.pdf: 2463662 bytes, checksum: db1006c64be351ea8d3925a544571f33 (MD5) Dissertação - Rogerio Mastrela - 2014.pdf: 2463662 bytes, checksum: db1006c64be351ea8d3925a544571f33 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2015-02-20T10:48:22Z (GMT). No. of bitstreams: 3 Dissertação - Rogerio Mastrela - 2014.pdf: 2463662 bytes, checksum: db1006c64be351ea8d3925a544571f33 (MD5) Dissertação - Rogerio Mastrela - 2014.pdf: 2463662 bytes, checksum: db1006c64be351ea8d3925a544571f33 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2014-08-07 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / The research reported in this work aims to investigate the contribution of using the methodologies “Mathematical Modeling” and “Information and Communication Technologies” (ICTs) in the teaching-learning process of some mathematical concepts, namely: percentage, rule of three, interest, tables and graphs. These concepts were developed in a way that enable involved students relate them to their quotidian. The study was developed in a class of eighth grade (8th grade) of the Basic School at the Municipal School "Arminda Rosa de Mesquita", located in the rural area of Catalão-Goiás. Questionnaires, field diary and filming were the tools used and analyzed from a qualitative and quantitative approach. This analysis revealed evidences that the used methodologies brought advances in analytical and critical development of the involved students, as well as helped to develop the skills of logical reasoning, problem solving and argumentation. Students acted as builders of their own knowledge through interaction among themselves and with the teacher, who became an advisor. Furthermore, it could be verified that Mathematical Modeling and ICTs make students feel a great pleasure, because they are dealing with everyday situations. And working with computers gave new meaning to the contents studied. / A pesquisa relatada neste trabalho tem como propósito investigar a contribuição da utilização das metodologias Modelagem Matemática e das Tecnologias da Informação e Comunicação (TIC´s) no processo de ensino-aprendizagem de alguns conceitos matemáticos, a saber: porcentagem, regra de três, juros, tabelas e gráficos. Estes conceitos foram trabalhados visando permitir a cada aluno envolvido relacioná-los com seu cotidiano. O trabalho foi desenvolvido em uma turma de oitavo ano (8°ano) do Ensino Fundamental da Escola Municipal “Arminda Rosa de Mesquita”, situada na zona rural do município de Catalão-Goiás. Foram utilizados, como instrumentos mediadores do processo: questionários, diário de campo e filmagens, os quais foram analisados a partir de uma abordagem qualitativa e quantitativa. Com a análise dos dados obtidos foi possível perceber que a metodologia utilizada trouxe indícios de avanços no desenvolvimento analítico e crítico dos envolvidos, além de possibilitar o desenvolvimento das habilidades de raciocínio lógico, de resolução de problemas e de argumentação. Os alunos atuaram como construtores do próprio conhecimento através da interação entre eles e com o professor, que passou a ter um papel de orientador. Além disso, verificou-se que, ao trabalhar em conjunto a modelagem com as TIC’s, os alunos sentem um grande prazer, pois lidam com situações cotidianas. E trabalhar com a informática deu um novo sentido aos conteúdos estudados.

Made available in DSpace on 2016-04-27T16:58:47Z (GMT). No. of bitstreams: 1 David Luiz Mazzanti.pdf: 2133856 bytes, checksum: 42bf84db8b1bbaacf676eaac575aceed (MD5) Previous issue date: 2008-10-27 / Secretaria da Educação do Estado de São Paulo / This study is a qualitative research that aims to looked at four pairs of students in the 3rd grade of high school segment of the education of the Education of Young and Adults (EJA) from a public school and the central municipality of Franco da Rocha. These students solved problems four situations-problems, which were guided by the Ethnomathematics Ubiratan D'Ambrosio (1975), involving the Calculations labor using the mathematical concepts and Percentage of Rule of Three. Focus our research seeking to answer the following questions: 1) Why do students of the EJA have both interest and curiosity in learning calculations labor? What are those interests? 2) What have previous knowledge that students of EJA need for the resolution of situations-problem involving the calculations labor? 3) What are the difficulties presented by students of the EJA when solve situations-problem involving the calculations labor? 4) What impact caused when the math is presented in a contextualized way to the life of pupils of EJA? We used two instruments for research, the Instrument 1 that identified the labor concepts that the students surveyed had an interest in knowing and learning and Instrument 2 composed of four-problem situations and developed after the Instrument 1. Using us as some elements of the engineering teaching, we seek to build situations that could lead students to an autonomous stance with problem-solving strategies proposed, engaging them and making them actors of the learning process. Both search engines were sufficient to answer the four questions proposed above, and consequently the results were satisfactory, indicating that contextualizing the teaching of rule of three percent and the calculations using labor, the impact on the lives of students is seen so positive, making the learning process more meaningful / Este estudo é uma pesquisa qualitativa que tem como objetivo analisar quatro duplas de alunos da 3ª série do Ensino Médio do segmento de ensino da Educação de Jovens e Adultos (EJA) de uma escola pública e central do município de Franco da Rocha. Esses alunos resolveram quatro situações-problemas contextualizadas, que foram norteadas pela Etnomatemática de Ubiratan D Ambrósio (1975), envolvendo os Cálculos Trabalhistas utilizando os conceitos matemáticos de Porcentagem e Regra de Três. Focamos nossa pesquisa buscando responder às seguintes questões: 1) Por que os alunos da EJA têm tanto interesse e curiosidade na aprendizagem dos cálculos trabalhistas? Quais são esses interesses? 2) Quais os conhecimentos prévios que os alunos da EJA necessitam para a resolução de situações-problema envolvendo os cálculos trabalhistas? 3) Quais as dificuldades apresentadas pelos alunos da EJA quando solucionam situações-problema que envolvam os cálculos trabalhistas? 4) Qual o impacto causado quando a matemática é apresentada de uma maneira contextualizada para a vida dos alunos da EJA? Utilizamos dois instrumentos de pesquisa, o Instrumento 1 que identificava os conceitos trabalhistas que os alunos pesquisados tinham o interesse em conhecer e aprender e o Instrumento 2 composto de quatro situações-problema e elaborado após o Instrumento 1. Utilizando-nos assim de alguns elementos da engenharia didática, buscamos construir situações que levassem os alunos a uma atitude autônoma com estratégias de resolução de problemas propostos, engajando-os e tornando-os atores do processo de aprendizagem. Os dois instrumentos de pesquisa foram suficientes para responder as quatro questões propostas acima e, em conseqüência os resultados obtidos foram satisfatórios, o que revela que contextualizando o ensino de regra de três e porcentagem utilizando os cálculos trabalhistas, o impacto na vida dos alunos é visto de maneira positiva, tornado o processo de aprendizagem mais significativo

Research Doctorate - Doctor of Philosophy (PhD) / Interval estimation of the Binomial parameter è, representing the true probability of a success, is a problem of long standing in statistical inference. The landmark work is by Bayes (1763) who applied the uniform prior to derive the Beta posterior that is the normalised Binomial likelihood function. It is not well known that Bayes favoured this ‘noninformative’ prior as a result of considering the observable random variable x as opposed to the unknown parameter è, which is an important difference. In this thesis we develop additional arguments in favour of the uniform prior for estimation of è. We start by describing the frequentist and Bayesian approaches to interval estimation. It is well known that for common continuous models, while different in interpretation, frequentist and Bayesian intervals are often identical, which is directly related to the existence of a pivotal quantity. The Binomial model, and its Poisson sister also, lack a pivotal quantity, despite having sufficient statistics. Lack of a pivotal quantity is the reason why there is no consensus on one particular estimation method, more so than its discreteness: frequentist (unconditional) coverage depends on è. Exact methods guarantee minimum coverage to be at least equal to nominal and approximate methods aim for mean coverage to be close to nominal. We agree with what seems like the majority of frequentists, that exact methods are too conservative in practice, and show additional undesirable properties. This includes more recent ‘short’ exact intervals. We argue that Bayesian intervals based on noninformative priors are preferable to the family of frequentist approximate intervals, some of which are wider than exact intervals for particular data values. A particular property of the interval based on the uniform prior is that its mean coverage is exactly equal to nominal. However, once committed to the Bayesian approach there is no denying that the current preferred choice, by ‘objective’ Bayesians, is the U-shaped Jeffreys prior which results from various methods aimed at finding noninformative priors. The most successful such method seems to be reference analysis which has led to sensible priors in previously unsolved problems, concerning multiparameter models that include ‘nuisance’ parameters. However, we argue that there is a class of models for which the Jeffreys/reference prior may be suboptimal and that in the case of the Binomial distribution the requirement of a uniform prior predictive distribution leads to a more reasonable ‘consensus’ prior.