No description available.

<p>Recent advances in technology have allowed researchers to collect high-dimensional biological data simultaneously. In genomic studies, for instance, measurements from tens of thousands of genes are taken from individuals across several experimental groups. In time course microarray experiments, gene expression is measured at several time points for each individual across the whole genome resulting in massive amount of data. In such experiments, researchers are faced with two types of high-dimensionality. The first is global high-dimensionality, which is common to all genomic experiments. The global high-dimensionality arises because inference is being done on tens of thousands of genes resulting in multiplicity. This challenge is often dealt with statistical methods for multiple comparison, such as the Bonferroni correction or false discovery rate (FDR). We refer to the second type of high-dimensionality as gene specific high-dimensionality, which arises in time course microarry experiments due to the fact that, in such experiments, sample size is often smaller than the number of time points ($n</p> <p>In this thesis, we use the growth curve model (GCM), which is a generalized multivariate analysis of variance (GMANOVA) model, and propose a moderated test statistic for testing a special case of the general linear hypothesis, which is specially useful for identifying genes that are expressed. We use the trace test for the GCM and modify it so that it can be used in high-dimensional situations. We consider two types of moderation: the Moore-Penrose generalized inverse and Stein's shrinkage estimator of $ S $. We performed extensive simulations to show performance of the moderated test, and compared the results with original trace test. We calculated empirical level and power of the test under many scenarios. Although the focus is on hypothesis testing, we also provided moderated maximum likelihood estimator for the parameter matrix and assessed its performance by investigating bias and mean squared error of the estimator and compared the results with those of the maximum likelihood estimators. Since the parameters are matrices, we consider distance measures in both power and level comparisons as well as when investigating bias and mean squared error. We also illustrated our approach using time course microarray data taken from a study on Lung Cancer. We were able to filter out 1053 genes as non-noise genes from a pool of 22,277 genes which is approximately 5\% of the total number of genes. This is in sync with results from most biological experiments where around 5\% genes are found to be differentially expressed.</p> / Master of Science (MSc)

In this thesis the two disciplines of Statistics and Artificial Neural Networks are combined into an integrated study of a data set of a weather modification Experiment. An extensive literature study on artificial neural network methodology has revealed the strongly interdisciplinary nature of the research and the applications in this field. An artificial neural networks are becoming increasingly popular with data analysts, statisticians are becoming more involved in the field. A recursive algoritlun is developed to optimize the number of hidden nodes in a feedforward artificial neural network to demonstrate how existing statistical techniques such as nonlinear regression and the likelihood-ratio test can be applied in innovative ways to develop and refine neural network methodology. This pruning algorithm is an original contribution to the field of artificial neural network methodology that simplifies the process of architecture selection, thereby reducing the number of training sessions that is needed to find a model that fits the data adequately. [n addition, a statistical model to classify weather modification data is developed using both a feedforward multilayer perceptron artificial neural network and a discriminant analysis. The two models are compared and the effectiveness of applying an artificial neural network model to a relatively small data set assessed. The formulation of the problem, the approach that has been followed to solve it and the novel modelling application all combine to make an original contribution to the interdisciplinary fields of Statistics and Artificial Neural Networks as well as to the discipline of meteorology. / Mathematical Sciences / D. Phil. (Statistics)

An exploratory study was undertaken to investigate the relationship between personality preference groupings, as described by Jung’s (1959) type theory, and emotional intelligence, as measured by Bar-On’s emotional intelligence quotient (Bar-On, 1997). The sample group consisted of 1 121 recruitment candidates for a South African investment bank. The sixteen personality types, as measured by the Myers-Briggs Type Indicator, were represented in the sample. The statistical analysis conducted for this study included comparison of means, correlation analysis and analysis of variance. The results indicated statistically significant relationships between the preferences of Extroversion, Judgement, their combined preference grouping and emotional intelligence. No statistically significant relationships were found between the preference groupings of Intuition and Thinking, Sensing and Thinking, Intuition and Feeling, and Sensing and Feeling. The preferred Feeling preference type consistently scored the lowest in terms of emotional intelligence scores. / Industrial and Organisational Psychology / M.A. (Industrial and Organisational Psychology

The aim of this thesis was to investigate the use of effect sizes to report the results of statistical credit rating models in a more practical way. Rating systems in the form of statistical probability models like logistic regression models are used to forecast the behaviour of clients and guide business in rating clients as “high” or “low” risk borrowers. Therefore, model results were reported in terms of statistical significance as well as business language (practical significance), which business experts can understand and interpret. In this thesis, statistical results were expressed as effect sizes like Cohen‟s d that puts the results into standardised and measurable units, which can be reported practically. These effect sizes indicated strength of correlations between variables, contribution of variables to the odds of defaulting, the overall goodness-of-fit of the models and the models‟ discriminating ability between high and low risk customers. / Statistics / M. Sc. (Statistics)

Le sujet de la présente étude est la violence scolaire, phénomène complexe et polysémique qui préoccupe légitimement le monde de l’éducation depuis plus de trente ans. À partir des analyses factorielles exploratoires, analyses de variance factorielle et finalement analyses multivariées de covariance, cette recherche vise plus précisément à dégager la relation entre le climat scolaire, le contexte scolaire et les différents rôles adoptés par les élèves du niveau secondaire lors d’une situation de violence scolaire. Les données de la présente étude ont été collectées par Michel Janosz et son équipe pendant l’année 2010, dans quatre établissements éducatifs provenant d’une commission scolaire de la grande région de Montréal. L’échantillon de départ est composé de 1750 élèves qui fréquentent des classes ordinaires et spéciales du premier et deuxième cycle du secondaire âgés entre 10 et 18 ans. Pour fins d’analyse, deux petites écoles ainsi que les classes spéciales ont été retirées. Il demeure donc 1551 élèves dans l’échantillon initial analysé. Les résultats des analyses permettent de constater d’une part, la relation significative existante entre les dimensions du climat scolaire et l’adoption des différents rôles lors d’une situation de violence scolaire, les climats d’appartenance et de sécurité étant les plus importants, et d’autre part d’observer des différences dans les perceptions que les élèves ont de la violence scolaire selon le niveau et selon l’école. / The present study pertains to a complex and polysemic phenomenon that has preoccupied people working in the field of education since at least thirty years, that is, school violence. Using factor analysis, analysis of variance and multivariate analysis of covariance, this research aims at exploring specifically the relationship between school climate, school context and the various roles adopted by students at the high school level when they face a situation in which school violence in present. Data for this study were collected by Michel Janosz and his team in 2010, within four schools, all in the same school board of the Montreal region. The original sample comprises 1750 students who attend both standard special classes, between 10 and 18 years of age. The analyses presented are based on a reduced sample where the special classes and the two small schools have been withdrawn. Therefore, the answers from 1551 student s are used. The results show that first, there is a significant relationship between the various dimensions of school climate and the different roles adopted by students facing a situation in which violence is present, perceptions of belonging and of security being the most important. Second, all things being equal, there are significant difference between schools, and school levels.

Diversos delineamentos experimentais que são aplicados correntemente tomam como base experimentos agronômicos. Esses dados experimentais são, geralmente, analisados usando-se modelos que consideram uma variância residual constante (ou homogênea), como pressuposto inicial. Entretanto, esta pressuposição mostra-se relativamente forte quando se está diante de situações para as quais fatores ambientais ou externos exercem considerável influência nas medidas experimentais. Neste trabalho, são estudados modelos para a média e a variância, simultaneamente, com a variância estruturada de duas formas: (i) por meio de um preditor linear, que permite incorporar variáveis externas e fatores de ruído e (ii) por meio de efeitos aleatórios, que permitem acomodar tanto o efeito longitudinal quanto o efeito de superdispersão, no caso de medidas binárias repetidas no tempo. A classe de modelos lineares generalizados duplos (MLGD) foi aplicada a um estudo observacional que consistiu em medir a mortalidade de frangos de corte no fim da condição de espera pré-abate. Nesse problema, é forte a evidência de que alguns fatores influenciam a variabilidade, e consequentemente, diminuem a precisão das análises inferenciais. Outro problema agronômico relevante, associado à horticultura, são os experimentos de cultura de tecidos vegetais, em que o número de explantes que regeneram são contados. Como esse tipo de experimento apresenta um grande número de parâmetros a serem estimados, comparado ao tamanho da amostra, os modelos existente podem gerar estimativas questionáveis ou até levar a conclusões erroneas, uma vez esse que são baseados em grandes amostras para se fazer inferência estatística. Foi proposto um modelo linear generalizados duplo, para os dados de proporções, de uma perspectiva Bayesiana, visando a análise estatística sob pequenas amostras e a incorporação do conhecimento especialista no processo de estimação dos parâmetros. Um problema clínico, que envolve dados binários medidos repetidamente no tempo é apresentado e são propostos dois modelos que acomodam o efeito da superdispersão e a dependência longitudinal das medidas, utilizandos-se efeitos aleatórios. Foram obtidos resultados satisfatórios nos três problemas estudados. Os MLGD permitiram identificar os fatores associados à mortalidade das aves de corte, o que permitirá minimizar perdas e habilitar os processos de manejo, transporte e abate aos critérios de bem-estar animal e exigências da comunidade européia. O MLGD Bayesiano permitiu identificar o genótipo associado ao efeito de superdispersão, aumentando a precisão da inferência de seleção de variedades. Dois modelos combinados foram propostos logit-normal-Bernoulli-beta e o probit-normal-Bernoulli-beta, que acomodaram satisfatoriamente a superdispersão e a dependência longitudinal das medidas binárias. Esses resultados reforçam a importância de se modelar a média e a variância conjuntamente, o que aumenta a precisão na pesquisa agronômica, tanto em estudos experimentais quanto em estudos observacionais. / Several experimental designs that are currently applied are based on agricultural experiments. These experimental data are, usually, analised with statistical models that assume constant residual variance (or homogeneous), as basic assumption. However, this assumption shows hard to stand for, when environmental or external factors exert strong influence over the measurements. In this work, we study the joint modelling for the mean and the variance, the latter being structured on two ways: (i) through a linear predictor, which allows the incorporation of external variables and/or noise factors and (ii) by the use of random effects, that accommodate jointly the possible overdispersion effect and the dependence of longitudinal data in the case of binary measusurements taken over time. The class of double generalized linear models (DGLM) was applied to an observational study where the poultry mortality was measured in the preslaughter operations. With this situation, it can be observed that there is a strong influence from some environmental factors over the variability observed, and consequently, this reduces the precision of the inferential analysis. Another relevant agricultural problem, related to horticulture, is the tissue culture experiments, where the number of regenerated explants is counted. Usually, this kind of experiment use a large number of parameters to be estimated, when compared with the sample size. The current frequentist models are based on large samples for statistical inference and, under this experimental condition, can generate unreliable estimates or even lead to erroneous conclusions. A double generalized linear model was proposed to analyse proportion data, under the Bayesian perspective, which can be applied to small samples and can incorporate expert knowledge into the parameter estimation process. One clinical research, that measured binary data repeatedly through the time is presented and two models are proposed to fit the overdispersion effect and the dependence of longitudinal measurements, using random effects. It was obtained satisfactory results under these three problems studied. the DGLM allowed to identify factors associated with the poultry mortality, that will allow to minimize loss and improve the process, since the catching until lairage on slaughterhouse, agreeing with animal welfare criteria and the European community rules. The Bayesian DGLM allowed to identify the genotype associated with the overdispersion effect, increasing the precision on the inference about varieties selection. Two combined models were proposed, a logit-normal- Bernoulli-beta and a probit-normal-Bernoulli-beta, which have both addressed the overdispersion effect and the longitudinal dependence of the binary measurements. These results reinforce the importance to modelling mean and dispersion jointly, as a way to increase the precision of agricultural experimentation, be it on experimental studies or observational studies.

A utilização de produtos provenientes de fontes renováveis e livres de substâncias tóxicas é tendência global, prova disso é o constante aumento da demanda por produtos à base de madeira. Segundo o Forest Products Statistics (2015), a produção mundial de painéis de madeira reconstituída, em 2014, foi de 388 milhões de m³, um aumento de 5,5% em comparação com o ano anterior e um aumento de 34% quando comparado com 2010. No entanto, o setor industrial de painéis de madeira há décadas enfrenta um grande desafio com relação às emissões tóxicas vindas dos adesivos convencionais. Diante destes problemas, a proposta do presente trabalho foi testar a viabilidade da produção de painéis aglomerados e painéis OSB, com significativa redução da emissão de formaldeído, a partir de resíduos de madeira de Pinus sp. e Tectona grandis (Teca). Neste sentido, buscou-se contribuir para o aumento do conhecimento científico sobre a utilização do polímero natural polihidroxibutirato (PHB) e do resíduo de tinta à base de resina epóxi como adesivos alternativos. Os painéis foram fabricados variando-se os parâmetros de produção para obtenção de melhores condições de processo, sendo estes: densidade baixa, média e alta; teor de adesivo de 20, 30 e 40%; adição de partículas de Teca nas proporções de 0, 25, 50, 75, 100%. O desempenho físico-mecânico dos painéis foi avaliado com base nas normas ABNT NBR 14810 (2013) e ANSI A208.1 (2009). Realizou-se análise de variância (ANOVA) para testar a influência dos fatores individuais (densidade, percentual de adesivo e fração de Teca), além das interações entre tais fatores nas propriedades físico-mecânicas dos painéis. Os resultados apontaram para excelentes propriedades físicas e mecânicas dos painéis aglomerados de média e alta densidade, tendo resíduo de tinta, principalmente, nas proporções de 30 e 40%. Na maioria dos casos as propriedades de tais painéis foram superiores aos requisitos estipulados pela norma brasileira e pelas internacionais. Assim, ficou confirmada a viabilidade de produção dos aglomerados com pelo menos um dos insumos estudados bem como seu potencial de emprego para as finalidades compatíveis com produtos desta natureza. / The use of products from renewable sources and free of toxic substances is a global trend, the proof is the steady increase in demand for wood-based products. According to the Forest Products Statistics (2015), world production of reconstituted wood panels in 2014 was 388 million cubic meters, an increase of 5.5% compared to the previous year and an increase of 34% compared to 2010. However, the industrial sector of wood panels for decades faces a major challenge with regard to toxic emissions coming from conventional adhesives. Faced with these problems, the purpose of this study was to test the feasibility of production of panels and OSB panels, with significant reduction of formaldehyde emissions from wood waste Pinus sp. and teak (Teak). In this sense, we sought to contribute to the increase of scientific knowledge on the use of natural polymer polyhydroxybutyrate (PHB) and residual ink resin-based epoxy as alternative adhesives. The panels were manufactured by varying the production parameters to obtain the best processing conditions, namely: low density, medium and high; resin content of 20, 30 and 40%; adding particles of Teak in proportions of 0, 25, 50, 75, 100%. The physical-mechanical performance of the panels was evaluated based on the standards NBR 14810 (2013) and ANSI A208.1 (2009). Held analysis of variance (ANOVA) to test the influence of individual factors (density, adhesive percentage and fraction Teak), and the interactions among these factors in the physical-mechanical properties of the panels. The results showed excellent physical and mechanical properties of the panels average clusters and high density, and ink residue, mainly in the proportions of 30 and 40%. In most cases the properties of these boards were superior to the requirements set by the Brazilian and international standards. Thus, it was confirmed production of agglomerates with at least one viability of inputs studied as well as their potential for employment for purposes compatible with products of this nature.

The teratogenic potential of commercial formulations of atrazine (40.8%) and 2,4-D was evaluated using FETAX (frog embryo teratogenic assay--Xenopus). Because these herbicides have been detected in ground and surface water, this study was designed to determine the adverse effects in buffer and natural water for both herbicides. All treatments showed a significant concentration-response effect on exposed embryos, except for the 2,4-D natural water sample. Atrazine (solubility of the commercial formula used 70 mg/L at 20 degrees C), compared to 2,4-D (solubility = 311 mg/L at pH = 1 and 25 degrees C), had a significantly greater teratogenic effect in both the buffer (atrazine EC50 = 33 mg/L, LC50 = 100 mg/L, TI = 3.03; 2,4-D EC50 = 245 mg/L, LC50 = 254 mg/L, TI = 1.04) and natural water samples (atrazine EC50 < 8 mg/L, LC50 = 126 mg/L; 2,4-D EC50 and LC50 > 270 mg/L). The 2,4-D EC50 and LC50 values for the buffer were similar at 245 mg/L and 254 mg/L. These similar values and the teratogenic index (TI) of 1.04 suggested that 2,4-D was more embryotoxic than teratogenic to frog embryos at high concentrations. Atrazine in natural water demonstrated a significantly greater EC50 (100% abnormality at 8 mg/L, the lowest test concentration) to frog embryos than the buffer experiment (EC50 = 33 mg/L). The extrapolated lowest observable adverse effect concentration (LOAEC) for the natural water experiment was 1.1 mg/L. These results suggest that atrazine toxicity is enhanced by the synergistic or additive effects of some component of the water or atrazine was already present in the sample. In contrast to atrazine, 2,4-D was less toxic in natural water than buffer. These results suggest that both atrazine and 2,4-D pose little threat, since their embryotoxicity and teratogenicity to frog embryos occur at high concentrations approaching their maximum solubility levels in water.

<p>У оквиру истраживања ове докторске дисертације креиран је нови<br />оригинални метод за идентификацију опасних места на путевима<br />заснован на континуалној анализи варијансе (АНОВЕ). Метод, на основу<br />статистичких показатеља даје одређене карактеристике<br />(сигнификантности) односно разлике или сличности између<br />посматраних група. Под појмом &bdquo;група&ldquo; подразумевају се краће путне<br />деонице пута стандардне дужине (суб-деонице) на којима се у<br />одређеном временском периоду десио одређени број саобраћајних<br />незгода. Међусобним поређењем тих група (суб-деоница), као и<br />поређењем тих група (суб-деоница) са целим скупом (целом<br />посматраном путном деоницом коју чине све суб-деонице), добијају се<br />одређене статистичке вредности сигнификантности односно значајности<br />разлике или сличности међу њима. Ти показатељи дају одговарајуће<br />оцене посматраних суб-деоница у погледу безбедности односно не<br />безбедности тих суб-деоница.</p> / <p>U okviru istraživanja ove doktorske disertacije kreiran je novi<br />originalni metod za identifikaciju opasnih mesta na putevima<br />zasnovan na kontinualnoj analizi varijanse (ANOVE). Metod, na osnovu<br />statističkih pokazatelja daje određene karakteristike<br />(signifikantnosti) odnosno razlike ili sličnosti između<br />posmatranih grupa. Pod pojmom &bdquo;grupa&ldquo; podrazumevaju se kraće putne<br />deonice puta standardne dužine (sub-deonice) na kojima se u<br />određenom vremenskom periodu desio određeni broj saobraćajnih<br />nezgoda. Međusobnim poređenjem tih grupa (sub-deonica), kao i<br />poređenjem tih grupa (sub-deonica) sa celim skupom (celom<br />posmatranom putnom deonicom koju čine sve sub-deonice), dobijaju se<br />određene statističke vrednosti signifikantnosti odnosno značajnosti<br />razlike ili sličnosti među njima. Ti pokazatelji daju odgovarajuće<br />ocene posmatranih sub-deonica u pogledu bezbednosti odnosno ne<br />bezbednosti tih sub-deonica.</p> / <p>In the framework of the research of this doctoral dissertation, a new original<br />method for the identification of dangerous locations on roads based on<br />continual analysis of variance (ANOVE) was created. The method, based on<br />statistical indicators, gives certain characteristics (significance), ie differences<br />or similarities between the observed groups. The term &quot;group&quot; means shorter<br />road sections of standard length (subsections) where a certain number of<br />traffic accidents occurred during a certain period of time. By comparing these<br />groups (subsections) with each other, as well as by comparing these groups<br />(subsections) with the whole set (the entire observed road section consisting<br />of all subsections), certain statistical values of significance or significance of<br />the difference or similarity between them are obtained. These indicators<br />provide appropriate assessments of the observed subsections in terms of the<br />safety or not the safety of these subsections.</p>