Maximally selected statistics for the estimation of simple cutpoint models are embedded into a generalized conceptual framework based on conditional inference procedures. This powerful framework contains most of the published procedures in this area as special cases, such as maximally selected chi-squared and rank statistics, but also allows for direct construction of new test procedures for less standard test problems. As an application, a novel maximally selected rank statistic is derived from this framework for a censored response partitioned with respect to two ordered categorical covariates and potential interactions. This new test is employed to search for a high-risk group of rectal cancer patients treated with a neo-adjuvant chemoradiotherapy. Moreover, a new efficient algorithm for the evaluation of the asymptotic distribution for a large class of maximally selected statistics is given enabling the fast evaluation of a large number of cutpoints. / Series: Research Report Series / Department of Statistics and Mathematics

Learning to comply with parental commands and requests is an important developmental achievement during toddlerhood. Although more responsive parenting often is associated with increases in children's compliance during the toddler years, the role of mothers' and toddlers' language abilities on change in compliance has largely been ignored. The current study addressed this gap using a sample of low-income, primarily African American mothers and toddlers (N = 55). Two models examining the role of receptive vocabulary were evaluated. First, mothers with higher receptive vocabulary scores were hypothesized to display more warm responsive communication in a teaching situation, which would be related to higher children's receptive vocabulary scores, and increased child compliance from age 2 to 3. Conversely, mothers with lower receptive vocabulary scores were expected to use more hostile intrusive communication, or communication patterns that would predict lower receptive vocabulary scores in children and increases in noncompliance over the third year. While direct associations were supported linking mothers' communication style with mothers' receptive vocabulary and change in compliance and noncompliance from age 2 to age 3, mediational hypotheses were not supported. The results of this study, while limited by small sample size, indicate that mothers' use of warm responsive or hostile intrusive communication in teaching situations affects their toddlers' development of compliance and noncompliance during the third year of life.

The supLM test for structural change is embedded into a permutation test framework for a simple location model. The resulting conditional permutation distribution is compared to the usual (unconditional) asymptotic distribution, showing that the power of the test can be clearly improved in small samples. Furthermore, generalizations are discussed for binary and multivariate dependent variables as well as model-based permutation testing for structural change. The procedures suggested are illustrated using both artificial and real-world data (number of youth homicides, employment discrimination data, structural-change publications, and stock returns). / Series: Research Report Series / Department of Statistics and Mathematics

Os índices de evasão e fracasso escolar no ensino fundamental no Brasil, nos dias atuais, ainda são alarmantes. Torna-se importante o planejamento de procedimentos que minimizem as dificuldades envolvidas no aprendizado da leitura e escrita e potencializem a aquisição dessas habilidades. Nessa direção, vários grupos de pesquisadores têm focado seus estudos, através do paradigma de equivalência, visando identificar as variáveis relacionadas com a formação de classes de equivalência e suas relações com a leitura, trazendo nítidas implicações educacionais. Porém, quando a leitura com compreensão é adquirida, não significa necessariamente que o leitor esteja sob controle das unidades verbais menores do que a palavra. O presente estudo teve como objetivo investigar variáveis relevantes no processo da emergência do controle por unidades mínimas e, portanto, da leitura recombinativa, com cinco crianças pré-escolares. Foi utilizado o programa EQUIV, em que foram ensinadas as relações entre palavra ditada e palavra impressa correspondente (AC); em seguida testadas a leitura de novas palavras, formadas pela recombinação das unidades menores presentes nas palavras ensinadas previamente. O programa era constituído de vinte fases, que se dividiam em cinco tipos básicos de procedimentos: Pré-Teste, Pré-Treino, Treinos, Testes e Pós-testes. Os dados demonstraram que três participantes apresentaram desempenhos próximos de 100% nos Testes de Leitura Recombinativa, indicando transferência das funções discriminativas das unidades mínimas das palavras de treino para as novas palavras. Nos pós-testes todos os participantes foram capazes de nomear palavras e sílabas as quais não eram capazes de nomear anteriormente. Nos testes de Equivalência realizados ao final do programa, os mesmos três participantes obtiveram desempenhos próximos de 100%, o que indica leitura com compreensão. Os resultados do presente estudo indicam que a ausência dos treinos das relações entre palavra ditada e figuras (AB) e dos Testes de Equivalência, não impediram a emergência do controle por unidades mínimas, sugerindo um procedimento mais econômico para a obtenção da leitura recombinativa. Portanto, o ganho de se instalar o controle por unidades mínimas mais rapidamente, suscita questões teóricas e sugere pesquisas futuras nessa direção. / The percentage of drop outs in Brazilian primary school is still alarming. It is important, though, to arrange procedures that minimize difficulties in reading and writing and maximize the acquisition of these abilities. In this direction, many groups of researchers have focused in studies in which through equivalence paradigm they identify variables related with the formation of equivalences class and its relations with reading comprehension. But when reading comprehension is acquired, it does not necessarily means that the reader is under the control of minimal verbal units of the word. The present study aimed to investigate the relevant variables in the process of emergence of minimal unit control and recombinative reading, with five preschool children. Using EQUIV software, relations between oral and printed word (AC) were taught; afterwards, textual behavior of novel words were tested, which were composed by minimal units of the words taught previously. The program consisted of twenty experimental phases, divided into four basic types: Pretest, Pretraining, Training and Post- Test. The results showed that three participants presented recombinative reading closer to 100% correct performances, indicating transfer of discriminative functions of the minimal units trained to new words. In Post- Tests, all participants developed repertoire of naming oral words and syllables that werent able to name before. In Equivalence Tests applied in the final phase, the same three participants obtained performance closer to 100%, indicating reading comprehension. The results of the present study point that the absence of training relations between oral word and picture (AB) and Equivalence Tests, didnt inhibit the emergence of control by minimal units, suggesting economy in the procedures of recombinative reading. Hence, the quicker installment of minimal verbal units control than previous studies generates theoretical questions and suggests future researches in this direction.

As etapas envolvidas na produção de uma mina podem ser modeladas e gerenciadas de forma mais eficiente quando há um fluxo mútuo e contínuo de informações, que vão desde a geologia até às especificações do produto final. Através da modelagem e gerenciamento das diversas etapas envolvidas no processo mineiro é possível melhorar significativamente o planejamento e operação das minas. A incorporação de componentes tecnológicos diversos tais como software de mineração, software de realidade virtual e componentes wireless, permite tomar decisões baseadas em modelos mais realísticos e precisos. Para tal, é proposta uma metodologia de integração destas tecnologias no controle das tarefas de decapeamento no planejamento de lavra de curto prazo, visando aprimorar o controle de qualidade no minério lavrado através do uso de técnicas de simulação condicional. A integração dessas tecnologias permite a transmissão de dados em tempo real entre planejamento e operação de mina, proporcionando melhorias na produtividade, na eficiência e no controle dos processos, além de promover melhorias na qualidade do material lavrado através do conhecimento do nível de incerteza associado em cada plano operacional de lavra. Uma solução composta por tecnologias integradas permite que o pessoal de operação de mina alcance os resultados de forma mais rápida e eficiente, melhorando significativamente a produtividade das operações da mina e a qualidade do minério lavrado. / The stages involved in mining production can be modeled and managed in a more efficient way when there is an integrated and continuous flow of information, from geology all the way down the mine value chain to the final specifications of the product. It is possible to improve the efficiency of decision-making in mine planning and operations through proper data-flow management. With the incorporation of technological components such as mining software, virtual reality software and wireless components, it is possible to take decisions based on models that are more accurate and realistic. This research considers a methodology technology integration for the tasks of waste moving in the short term mine planning, to improve the quality control in mined ore using conditional simulation techniques. The integration of these technologies allows instantaneous transmission of data between mine planning and the mine operation, improving productivity and efficiency in process control. In addition, it provides a measure of the uncertainty associated with the operational mining planning. An integrated solution allows mine planners and equipment operators to obtain quicker and more efficient results, improving significantly productivity in the operation of the mine and quality of the mined ore.

Campos Aleatórios Condicionais são modelos probabilísticos discriminativos que tem sido utilizados com sucesso em diversas áreas como processamento de linguagem natural, reconhecimento de fala e bioinformática. Entretanto, implementar algoritmos eficientes para esse tipo de modelo não é uma tarefa fácil. Nesse trabalho apresentamos um arcabouço que ajuda no desenvolvimento e experimentação de Campos Aleatórios Condicionais Semi Markovianos (semi-CRFs). Desenvolvemos algoritmos eficientes que foram implementados em C++ propondo uma interface de programação flexível e intuitiva que habilita o usuário a definir, treinar e avaliar modelos. Nossa implementação foi construída como uma extensão do arcabouço ToPS que, inclusive, pode utilizar qualquer modelo já definido no ToPS como uma função de característica especializada. Por fim utilizamos nossa implementação de semi-CRF para construir um preditor de promotores que apresentou performance superior aos preditores existentes. / Conditional Random Fields are discriminative probabilistic models that have been successfully used in several areas like natural language processing, speech recognition and bioinformatics. However, implementing efficient algorithms for this kind of model is not an easy task. In this thesis we show a framework that helps the development and experimentation of Semi-Markov Conditional Random Fields (semi-CRFs). It has an efficient implementation in C++ and an intuitive API that allow users to define, train and evaluate models. It was built as an extension of ToPS framework and can use ToPS probabilistic models as specialized feature functions. We also use our implementation of semi-CRFs to build a high performance promoter predictor.

Simulação geoestatística compreende uma variedade de técnicas que permitem gerar cenários que reproduzem a continuidade espacial e o histograma do fenômeno de interesse. Essas técnicas podem ser usadas para ajudar nas tomadas de decisões, permitindo um acesso à incerteza nas funções de resposta (que dependem dos cenários simulados), geralmente por meio de uma relação não-linear (retorno financeiro, recuperação geometalúrgica...). No entanto, uma de suas limitações é que as simulações podem demandar um tempo considerável para serem executadas em grandes depósitos. E a motivação dessa dissertação se concentra justamente nesse fato, buscando uma alternativa para acelerar o processamento computacional dessas simulações. A opção escolhida para isso foi desenvolver a Simulação via Múltiplos Passeios Aleatórios, que é uma nova abordagem para se realizar simulações geoestatística. Ela combina a krigagem com a simulação de passeios aleatórios independentes, de modo a gerar cenários simulados de uma maneira mais rápida que os algoritmos tradicionais. Essa dissertação apresenta detalhes do método e importantes contribuições desenvolvidas para melhorar o desempenho e a qualidade dos resultados gerados com o método. Foi também desenvolvido um software específico para possibilitar um uso simples, prático e rápido da técnica em qualquer situação (2D ou 3D). Estudos de caso foram feitos para checar a validade das simulações, que demonstraram boa reprodução dos histogramas e variogramas, além de um ganho de velocidade considerável, alcançando uma aceleração de até 5,65 x (em comparação com a Simulação por Bandas Rotativas) na simulação de um depósito de ferro em 3D, desempenho que pode ser melhor ainda à medida que mais dados amostrais estão disponíveis. / Geostatistical simulation comprises a variety of techniques, which allow the generation of multiple scenarios reproducing the spatial continuity and the histogram of the desired phenomenon (grades for instance). These methods can be used in the decision making process, allowing the assess to the uncertainty of functions responses (which depend on the simulated inputs) commonly through a non-linear relationship (net present value, interest tax return, ore geometallurgical recovery…). However, one of their limitations is that running simulation can take a considerable processing time to be executed in large deposits or large grids. Therefore, the motivation of this dissertation focuses on this fact, leading to the main goal, i.e. investigating an alternative to accelerate the simulation process. The option chosen is based on the development and adaptation of the Multiple Random Walk Simulation, which is algorithm to build geostatistical simulations. It combines kriging with the simulation of independent random walks in order to generate simulated scenarios faster than via traditional simulation algorithms. This dissertation presents details of the method and new important contributions developed to improve its performance and statistics reproduction. An algorithm and software was also presented in order to allow a simple, practical and fast use of the method in any condition (2D or 3D). Case studies were developed to check the validity of the simulations, which showed good reproduction of histogram and variograms, in addition to a considerable speed gain, achieving an acceleration up to 5.65 x (in comparison with Turning Bands Simulation) in the simulation of a 3D iron deposit, performance that can be enhanced as more conditioning samples are available.

Os índices de evasão e fracasso escolar no ensino fundamental no Brasil, nos dias atuais, ainda são alarmantes. Torna-se importante o planejamento de procedimentos que minimizem as dificuldades envolvidas no aprendizado da leitura e escrita e potencializem a aquisição dessas habilidades. Nessa direção, vários grupos de pesquisadores têm focado seus estudos, através do paradigma de equivalência, visando identificar as variáveis relacionadas com a formação de classes de equivalência e suas relações com a leitura, trazendo nítidas implicações educacionais. Porém, quando a leitura com compreensão é adquirida, não significa necessariamente que o leitor esteja sob controle das unidades verbais menores do que a palavra. O presente estudo teve como objetivo investigar variáveis relevantes no processo da emergência do controle por unidades mínimas e, portanto, da leitura recombinativa, com cinco crianças pré-escolares. Foi utilizado o programa EQUIV, em que foram ensinadas as relações entre palavra ditada e palavra impressa correspondente (AC); em seguida testadas a leitura de novas palavras, formadas pela recombinação das unidades menores presentes nas palavras ensinadas previamente. O programa era constituído de vinte fases, que se dividiam em cinco tipos básicos de procedimentos: Pré-Teste, Pré-Treino, Treinos, Testes e Pós-testes. Os dados demonstraram que três participantes apresentaram desempenhos próximos de 100% nos Testes de Leitura Recombinativa, indicando transferência das funções discriminativas das unidades mínimas das palavras de treino para as novas palavras. Nos pós-testes todos os participantes foram capazes de nomear palavras e sílabas as quais não eram capazes de nomear anteriormente. Nos testes de Equivalência realizados ao final do programa, os mesmos três participantes obtiveram desempenhos próximos de 100%, o que indica leitura com compreensão. Os resultados do presente estudo indicam que a ausência dos treinos das relações entre palavra ditada e figuras (AB) e dos Testes de Equivalência, não impediram a emergência do controle por unidades mínimas, sugerindo um procedimento mais econômico para a obtenção da leitura recombinativa. Portanto, o ganho de se instalar o controle por unidades mínimas mais rapidamente, suscita questões teóricas e sugere pesquisas futuras nessa direção. / The percentage of drop outs in Brazilian primary school is still alarming. It is important, though, to arrange procedures that minimize difficulties in reading and writing and maximize the acquisition of these abilities. In this direction, many groups of researchers have focused in studies in which through equivalence paradigm they identify variables related with the formation of equivalences class and its relations with reading comprehension. But when reading comprehension is acquired, it does not necessarily means that the reader is under the control of minimal verbal units of the word. The present study aimed to investigate the relevant variables in the process of emergence of minimal unit control and recombinative reading, with five preschool children. Using EQUIV software, relations between oral and printed word (AC) were taught; afterwards, textual behavior of novel words were tested, which were composed by minimal units of the words taught previously. The program consisted of twenty experimental phases, divided into four basic types: Pretest, Pretraining, Training and Post- Test. The results showed that three participants presented recombinative reading closer to 100% correct performances, indicating transfer of discriminative functions of the minimal units trained to new words. In Post- Tests, all participants developed repertoire of naming oral words and syllables that werent able to name before. In Equivalence Tests applied in the final phase, the same three participants obtained performance closer to 100%, indicating reading comprehension. The results of the present study point that the absence of training relations between oral word and picture (AB) and Equivalence Tests, didnt inhibit the emergence of control by minimal units, suggesting economy in the procedures of recombinative reading. Hence, the quicker installment of minimal verbal units control than previous studies generates theoretical questions and suggests future researches in this direction.

Water quality and river/stream ecosystems are important for all living creatures. To protect human health, aquatic life and the surrounding ecosystem, a considerable amount of time and money has been spent on sampling and monitoring streams and rivers. Water quality monitoring and analysis can help researchers predict and learn from natural processes in the environment and determine human impacts on an ecosystem. Measurements such as temperature, pH, nitrogen concentration, algae and fish count collected along the network are all important factors in water quality analysis. The main purposes of the statistical analysis in this thesis are (1) to assess the relationship between the variable measured in the water (response variable) and other variables that describe either the locations on/along the stream network or certain characteristics at each location (explanatory variable), and (2) to assess the degree of similarity between the response variable values measured at different locations of the stream, i.e. spatial dependence structure. It is commonly accepted that measurements taken at two locations close to each other should have more similarity than locations far away. However, this is not always true for observations from stream networks. Observations from two sites that do not share water flow could be independent of each other even if they are very close in terms of stream distance, especially those observations taken on objects that move passively with the water flow. To model stream network data correctly, it is important to quantify the strength of association between observations from sites that do not share water.

Logical statements are prevalent in mathematics, the sciences, law, and many areas of everyday life. The most common logical statements are conditionals, which have the form “If H..., then C...,” where “H” is a hypothesis (or condition) to be satisfied and “C” is a conclusion to follow. Reasoning about conditionals is a skill that is only superficially understood by most individuals and depends on four main conditional contexts (e.g., intuitive, abstract, symbolic, or counterintuitive). The purpose of this study was to test a theory about the effects of context ordering on reasoning about conditionals. To test the theory, the researcher developed, tested, and revised a virtual manipulative educational mathematics application, called the Learning Logic App. This study employed a convergent parallel mixed methods design to answer an overarching research question and two subquestions. The overarching research question was “How does the order of teaching four conditional contexts influence reasoning about conditionals?” The two subquestions examined this influence on reasoning in terms of performance and perceptions. This study involved two phases. During Phase I, 10 participants interacted with the Learning Logic App in a clinical setting. The researcher used information gathered in Phase I to revise the Learning Logic App for Phase II. During Phase II, 154 participants interacted with the Learning Logic App in a randomly assigned context ordering in an online setting. In both phases, the researcher collected quantitative and qualitative data. After independent analyses, the researcher made meta- inferences from the two data strands. The results of this study suggest that context ordering does influence learners’ reasoning. The most beneficial context ordering for learners’ performance was symbolic-intuitive-abstract-counterintuitive. The most beneficial context ordering for learners’ perceptions was intuitive-abstract-counterintuitive-symbolic. Based on these results, the researcher proposed a new context ordering: symbolic-intuitive-abstract-counterintuitive-symbolic. This progression incorporates a catalyst at the beginning (symbolic context) which aids the learner in reassessing their prior knowledge. Then, the difficulty of the contexts progresses from easiest to hardest (intuitive-abstract-counterintuitive-symbolic). These findings are important because they provide an instructional sequence for teaching and learning to reason about conditionals that is beneficial to both learners’ performance and their perceptions.