[pt] Um procedimento analítico é considerado apropriado para uma aplicação específica quando é capaz de gerar resultados confiáveis, que possibilitem a tomada de decisão com grau de confiança adequado, sendo sua adequação consolidada mediante a realização de ensaios de validação. Este trabalho propõe a utilização de um procedimento analítico alternativo, mais simples e econômico, baseado na técnica espectrofotométrica de absorção molecular, para quantificação de imidacloprid, um inseticida sistêmico, em amostras de solução aquosa. Foi demonstrado que o procedimento proposto é adequado ao uso pretendido descrevendo-se, detalhadamente, cada etapa da validação, considerando-se os limites estabelecidos para cada parâmetro de validação e aplicando-se técnicas estatísticas apropriadas na avaliação dos mesmos: análise de variância, análise de regressão, testes de significância, gráficos de controle e a estimativa da incerteza de medição. As incertezas de medição dos procedimentos de rotina e alternativo foram estimadas e comparadas às tolerâncias estipuladas, estabelecendo o procedimento alternativo como adequado. Uma comparação experimental deste procedimento com o de rotina (baseado em HPLC) foi realizada como parte do protocolo de validação. Além da avaliação do procedimento para quantificação de imidacloprid em nível de traços, foi investigada também a possibilidade de sua utilização, para a quantificação do mesmo ingrediente ativo em produtos formulados. Neste caso, foi demonstrado, através da comparação das incertezas estimadas às tolerâncias estabelecidas, que o procedimento alternativo não é adequado, por apresentar incertezas na ordem de aproximadamente 50% do valor destas tolerâncias, não possuindo assim o rigor metrológico requerido para esta aplicação. / [en] Fit for purpose analytical procedures must be sufficiently reliable to support any decision taken based on the generated results. In order to achieve that, consolidated adequacy evaluation of the analytical procedure must be obtained by performing validation experiments. In this work, an alternative and simpler spectrophotometric method for the quantification of imidacloprid in aqueous samples was compared to the HPLC-UV based reference method used in routine. The overall validation procedure started with a detailed description of each validation stage, followed by the settling of the limits for each of the validation parameters and then, applying the following statistical techniques to evaluate each of the parameters: ANOVA, regression analysis, significance tests, control charts and uncertainty estimation. The measurement of uncertainties estimation, based on ISO-GUM recommendations, was done for both analytical procedures (the alternative one and the reference one). After comparing these uncertainties with the tolerance values, the adequacy of the alternative proposed procedure was confirmed. Finally, by consolidating the validation, the experimental comparison of quantification methods was conducted. Besides evaluating the analytical procedure for trace-level imidacloprid quantification in water samples, the proposed method was also evaluated as the analytical procedure for imidacloprid based formulated products. In this case, it was demonstrated that the spectrophotometric method did not present the requested metrological requirements for such application, since the estimated uncertainties of the alternative procedure were about 50 % of the tolerance values.

Recent federal legislation has incentivized hospitals to focus on quality of patient care. A primary metric of care quality is patient readmissions. Many methods exist to statistically identify patients most likely to require hospital readmission. Correct identification of high-risk patients allows hospitals to intelligently utilize limited resources in mitigating hospital readmissions. However, these methods have seen little practical adoption in the clinical setting. This research attempts to identify the many open research questions that have impeded widespread adoption of predictive hospital readmission systems. Current systems often rely on structured data extracted from health records systems. This data can be expensive and time consuming to extract. Unstructured clinical notes are agnostic to the underlying records system and would decouple the predictive analytics system from the underlying records system. However, additional concerns in clinical natural language processing must be addressed before such a system can be implemented. Current systems often perform poorly using standard statistical measures. Misclassification cost of patient readmissions has yet to be addressed and there currently exists a gap between current readmission system evaluation metrics and those most appropriate in the clinical setting. Additionally, data availability for localized model creation has yet to be addressed by the research community. Large research hospitals may have sufficient data to build models, but many others do not. Simply combining data from many hospitals often results in a model which performs worse than using data from a single hospital. Current systems often produce a binary readmission classification. However, patients are often readmitted for differing reasons than index admission. There exists little research into predicting primary cause of readmission. Furthermore, co-occurring evidence discovery of clinical terms with primary diagnosis has seen only simplistic methods applied. This research addresses these concerns to increase adoption of predictive hospital readmission systems. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2017. / FAU Electronic Theses and Dissertations Collection

Esta Tese descreve o emprego da Análise por Injeção Sequencial (SIA) e de métodos estatísticos visando a otimização do tratamento de amostras da indústria de tintas através de Processos Oxidativos Avançados (POA\'s), mais especificamente através das reações de Fenton e foto-Fenton. Estudos foram realizados com o composto modelo vermelho de alizarina S para a otimização de parâmetros da reação de Fenton e o com sal tetrassódico de ácido 3,4′,4″,4″′-tetrassulfônico de ftalocianina de cobre para a otimização de parâmetros da reação de foto-Fenton em um foto-reator desenvolvido em laboratório. Nas condições obtidas com SIA, foi observada a degradação de 99,7% de alizarina e de 97% da ftalocianina de cobre. Uma amostra de efluente da indústria de tintas também foi considerada; para esta matriz, os resultados apontaram uma mineralização de 79% do efluente após a reação de foto-Fenton e de 45% após a reação de Fenton. / This Thesis describes the use of Sequential Injection Analysis (SIA) and statistical methods aiming the optimization of the treatment processes of coatings samples by Advanced Oxidative Processes (AOP\'s), specifically by Fenton and photo-Fenton reactions. Studies were performed with model compounds, alizarin red S for optimization of Fenton parameters and a copper phthalocyanine-3,4′,4″,4″′-tetrasulfonic acid tetrasodium salt dye for optimization of photo-Fenton parameters in a homemade photo reactor. At SIA established conditions, it was observed a degradation of 99.7% of alizarin and 97% of the phthalocyanine dye. A sample of wastewater from the coatings industry was also considered; for this matrix, results showed a sample mineralization of 79% after photo-Fenton and 45% after Fenton reactions.

Para a avaliação das características do solo relacionadas com o potencial uso dos solos, assim como para a avaliação da fertilidade, as análises químicas e físicas de rotina são os métodos convencionalmente usados. Estes são bastante custosos e demorados o que tem representado no Brasil uma dificuldade no seu uso por parte de pequenos agricultores, além da aplicabilidade da agricultura de precisão no manejo de solos. Atualmente a pedometria está fornecendo a possibilidade de incorporar em ciência do solo técnicas bastante sofisticadas que podem ajudar a diminuir o custo na obtenção da informação e compreender melhor o funcionamento dos processos do solo. Entre os tópicos mais recentes que estão incluídos na pesquisa relacionada com pedometria está a espectroscopia de reflectância. Embora se tenha demonstrado que uma grande quantidade de atributos podem ser estimados a partir da resposta espectral do solo via sensoriamento, ainda não se têm atingido níveis de acurácia ótimos em relação às metodologias convencionais, sobretudo no referente a atributos químicos. Para tanto, o presente trabalho foi desenvolvido com a finalidade de responder basicamente os seguintes questionamentos: a. Existem faixas espectrais específicas das bases trocáveis ou se estas podem mudar em função do argilomineral fornecedor da capacidade de troca de cátions?; b. A calibração de modelos usando unicamente algumas faixas espectrais específicas pode melhorar o desempenho destes?; c. Qual é a influência dos níveis de acurácia dos modelos espectrais sobre mapas construídos com atributos estimados a partir destes?; d. Como os tamanhos dos grupos de amostras de calibração influenciam a acurácia dos modelos?; e. Como a calibração de atributos relacionados com o intemperismo podem auxiliar no mapeamento de classes de solo? / The routine soil analysis is traditionally used on the evaluation of soil attributes related to land use potential, and the assessment of fertility. It is costly and time consuming, making it inaccessible for small farmers, and hampering the applicability of precision agriculture on soil management in Brazil. Currently, pedometrics is providing the possibility of incorporating in soil science sophisticated techniques that can help to reduce the cost of obtaining information and improve the understanding about how several soil processes works. One of the more recent topics on pedometrics is the soil reflectance spectroscopy. Through the soil reflected energy is possible to infer several soil properties, although optimum accuracy levels in the spectral estimation of soil attributes have not yet reached. In this sense, the aim of this study was basically answer the following questions: a. The exchangeable bases have specific spectral bands or the spectral responses of theses depends on the clay mineral?; b. the calibration of models by using only some specific spectral bands may improve the prediction performance?; c. What is the influence of the accuracy of prediction models on maps constructed with predicted soil attributes?; D. How calibration set size affect the accuracy of the models?; e. How the calibration of models for prediction of soil attributes related to soil weathering may assist the digital soil mapping?

Understanding where and why organisms are distributed in the environment are central themes in ecology. Animals live in environments in which they are subject to competing demands, such as the need to forage, to find mates, to reproduce, and to avoid predation. Optimal habitats for these various activities are usually distributed heterogeneously in the landscape and may vary both spatially and temporally, causing animals to adjust their locations in space and time to balance these conflicting demands. In this dissertation, I outline three studies of Procambarus fallax in the ridge-slough landscape of Water conservation Area 3A (WCS-3A). The first section outlines an observational sampling study of crayfish population distribution in a four hectare plot, where I statistically model the density distribution at two spatial scales. ... Secondly, I use radio telemetry to study individual adult crayfish movements at two study sites and evaluate habitat selection using Resource Selection Functions. In the third section, I test the habitat selection theory, ideal free distribution, by assessing performance measures (growth and mortality) of crayfish in the two major vegetation types in a late wet season (November 2007) and early wet season (August 2009). / by Craig van der Heiden. / Thesis (Ph.D.)--Florida Atlantic University, 2012. / Includes bibliographical references at the end of each chapter. / Mode of access: World Wide Web. / System requirements: Adobe Reader.

Change-point detection in hazard rate function is an important research topic in survival analysis. In this dissertation, we firstly review existing methods for single change-point detection in piecewise exponential hazard model. Then we consider the problem of estimating the change point in the presence of right censoring and long-term survivors while using Kaplan-Meier estimator for the susceptible proportion. The maximum likelihood estimators are shown to be consistent. Taking one step further, we propose an counting process based and least squares based change-point detection algorithm. For single change-point case, consistency results are obtained. We then consider the detection of multiple change-points in the presence of long-term survivors via maximum likelihood based and counting process based method. Last but not least, we use a weighted least squares based and counting process based method for detection of multiple change-points with long-term survivors and covariates. For multiple change-points detection, simulation studies show good performances of our estimators under various parameters settings for both methods. All methods are applied to real data analyses. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2014. / FAU Electronic Theses and Dissertations Collection

Made available in DSpace on 2016-08-10T10:40:37Z (GMT). No. of bitstreams: 1 CASSIA DA SILVA CASTRO ARANTES.pdf: 3047367 bytes, checksum: a63eab38d70349a1a580a883aa0f8bd3 (MD5) Previous issue date: 2016-03-10 / This study deals with the application of statistical methods for analysis of the quality production of the Meal and Degummed soybean Oil. As Case Study object has Guará Industry, which provided the necessary data. These were analyzed by applying statistical methods such as ANOVA and Tukey Test, stability analysis using control charts and process capability analysis. With the analysis came to the conclusion that the warehouse actually influence the quality of soybeans, the main feedstock of the company. It was also found that much of the quality characteristics of the products produced show that the processes are not stable and are unable. During the study, also rose at the main quality problems the company owned, as well as the causes of these. Finally, this work shows important information about the enterprise and suggests improvements to ensure effective gains in the quality of final products and consequently better results for the organization, preventing and eliminating unnecessary quality costs. / Este estudo aborda a aplicação de métodos estatísticos para análise da qualidade da produção de farelo e óleo degomado de soja. Como objeto do estudo de caso tem-se a Indústria Guará, a qual forneceu os dados necessários. Estes foram analisados aplicando-se métodos estatísticos, tais como Anova e Teste de Tukey, análise da estabilidade através de cartas de controle e análise da capacidade do processo. Com as análises, chegou-se à conclusão de que os armazéns realmente influenciam na qualidade da soja, principal matéria prima da empresa. Verificou-se também que grande parte das características de qualidade dos produtos produzidos demonstram que os processos não estão estáveis e não são capazes. Durante o estudo, foram levantados ainda os principais problemas de qualidade que a empresa possui, bem como as causas destes. Por fim, este trabalho demonstra importantes informações sobre a empresa e sugere melhorias para garantir ganhos efetivos na qualidade dos produtos finais e, consequentemente, melhores resultados para a organização, evitando e eliminando custos de qualidade desnecessários.

Os métodos de superfície de resposta e planejamento de experimentos foram utilizados no processo de análise e otimização de sistemas frigoríficos. Foram determinadas as dimensões do tubo capilar juntamente com a carga de refrigerante que proporcionaram as melhores condições de funcionamento a um protótipo. O comportamento de oito variáveis resposta foram estudadas, que são: Capacidade Frigorífica, Coeficiente de Eficácia, Temperatura de Descarga, Super Aquecimento, Sub resfriamento, Vazão de Refrigerante, Temperatura de Evaporação e Temperatura de Condensação. Superfícies de Resposta e Curvas de nível foram levantadas em diversas situações de interesse, visando revelar o comportamento e a sensibilidade do sistema. Alguns fatores revelaram níveis que propiciaram uma reduzida variabilidade para certas variáveis resposta demonstrando o conceito de sistema robusto. O método mostrou-se bastante adequado, contribuindo com resultados de grande valia para a otimização e análise do comportamento de sistemas frigoríficos, além de poder ter sua aplicabilidade ampliada para sistemas térmicos em geral. / The Response Surface Methodology and the Design of Experiments were applied on the analysis and optimization process of refrigeration systems. The dimensions of a capillary tube and refrigerant charge that provided the best working conditions to a prototype were determined. The behavior of the Refrigeration Capacity, Coeficient of Performance, Discharge Temperature, Super Heating, Sub Cooling, Mass Flow Rate, Evaporation Temperature and Condensing Temperature were studied in detail. Surface Response and Contour plots were constructed on many situations in order to reveal the system behavior and sensitivity. Some factor levels provided a small variability to certain responses, demonstrating the concept of robust system. The methodology contribuited properly with valuable results to the optimization and analysis of refrigeration system behavior; besides, its applicability can be easily generalised to thermal systems.

by Leung Hon-Kit. / Thesis (M.B.A.)--Chinese University of Hong Kong, 1992. / Includes bibliographical references (leaves 92-93). / ABSTRACT --- p.ii / TABLE OF CONTENTS --- p.iv / ACKNOWLEDGEMENTS --- p.vi / CHAPTER / Chapter I. --- INTRODUCTION --- p.1 / Chapter II. --- METHODOLOGY --- p.5 / "An Account of Telecommunications Deregulation in the U.S., U.K. and Japan" --- p.6 / Major Determinants of International Telephone Demand --- p.7 / Sources of Data --- p.7 / Analysis Method --- p.9 / Chapter III. --- MODELS AND RESULTS --- p.11 / Econometric --- p.11 / Box-Jenkins --- p.29 / Chapter IV. --- SUMMARY AND CONCLUSIONS --- p.38 / Multi-Carriers Effect --- p.39 / IVANS/Leased Circuit Effect --- p.41 / Price Elasticity of Demand --- p.42 / Impact on Dominant Carriers --- p.43 / Inference to Hong Kong Situtation --- p.44 / APPENDIXES --- p.46 / Chapter A. --- Traffic Statistics --- p.46 / Chapter B. --- Collection Charge Statistics --- p.54 / Chapter C. --- Economic Statistics --- p.56 / Chapter D. --- Charts of U.S. Telephone Traffic to Hong Kong and ARIMA Modelling --- p.59 / Chapter E. --- Charts of Hong Kong Telephone Traffic to US and ARIMA Modelling --- p.64 / Chapter F. --- Charts of UK Telephone Traffic to Hong Kong and ARIMA Modelling --- p.70 / Chapter G. --- Charts of Hong Kong Telephone Traffic to U.K. and ARIMA Modelling --- p.75 / Chapter H. --- Charts of Japan Telephone Traffic to Hong Kong and ARIMA Modelling --- p.80 / Chapter I. --- Charts of Hong Kong Telephone Traffic to Japan and ARIMA Modelling --- p.85 / Chapter J. --- Plots of Residuals of the Econometric Models --- p.90 / BIBLIOGRAPHY AND REFERENCE --- p.92

Pang Suet-Yee. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references (leaves 85-87). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Overview --- p.1 / Chapter 1.1.1 --- Survival Analysis --- p.2 / Chapter 1.1.2 --- Tree、-structured Statistical Method --- p.2 / Chapter 1.1.3 --- Mortality Study --- p.3 / Chapter 1.2 --- Motivation --- p.3 / Chapter 1.3 --- Background Information --- p.4 / Chapter 1.4 --- Data Content --- p.7 / Chapter 1.5 --- Thesis Outline --- p.8 / Chapter 2 --- Imputation and File Splitting --- p.10 / Chapter 2.1 --- Imputation of Missing Values --- p.10 / Chapter 2.1.1 --- Purpose of Imputation --- p.10 / Chapter 2.1.2 --- Procedure of Hot Deck Imputation --- p.11 / Chapter 2.1.3 --- List of Variables for Imputation --- p.12 / Chapter 2.2 --- File Splitting --- p.14 / Chapter 2.2.1 --- Splitting by Gender --- p.14 / Chapter 2.3 --- Splitting for Validation Check --- p.1G / Chapter 3 --- Cox Hazard Model --- p.17 / Chapter 3.1 --- Basic Idea --- p.17 / Chapter 3.1.1 --- Survival Analysis --- p.17 / Chapter 3.1.2 --- Survivor Function --- p.18 / Chapter 3.1.3 --- Hazard Function --- p.18 / Chapter 3.2 --- The Cox Proportional Hazards Model --- p.19 / Chapter 3.2.1 --- Kaplan-Meier Estimate and Log-Rank Test --- p.20 / Chapter 3.2.2 --- Hazard Ratio --- p.23 / Chapter 3.2.3 --- Partial Likelihood --- p.24 / Chapter 3.3 --- Extension of the Cox Proportional Hazards Model for Time-dependent Variables --- p.25 / Chapter 3.3.1 --- Modification of the Cox's Model --- p.25 / Chapter 3.4 --- Results of Model Fitting --- p.26 / Chapter 3.4.1 --- Extract the Significant Covariates from the Models --- p.31 / Chapter 3.5 --- Model Interpretation --- p.32 / Chapter 4 --- CART --- p.37 / Chapter 4.1 --- CART Procedure --- p.38 / Chapter 4.2 --- Selection of the Splits --- p.39 / Chapter 4.2.1 --- Goodness of Split --- p.39 / Chapter 4.2.2 --- Type of Variables --- p.40 / Chapter 4.2.3 --- Estimation --- p.40 / Chapter 4.3 --- Pruning the Tree --- p.41 / Chapter 4.3.1 --- Misclassification Cost --- p.42 / Chapter 4.3.2 --- Class Assignment Rule --- p.44 / Chapter 4.3.3 --- Minimal Cost Complexity Pruning --- p.44 / Chapter 4.4 --- Cross Validation --- p.47 / Chapter 4.4.1 --- V-fold Cross-validation --- p.47 / Chapter 4.4.2 --- Selecting the right sized tree --- p.49 / Chapter 4.5 --- Missing Value --- p.49 / Chapter 4.6 --- Results of CART program --- p.51 / Chapter 4.7 --- Model Interpretation --- p.53 / Chapter 5 --- Model Prediction --- p.58 / Chapter 5.1 --- Application to Test Sample --- p.58 / Chapter 5.1.1 --- Fitting test sample to Cox's Model --- p.59 / Chapter 5.1.2 --- Fitting test sample to CART model --- p.61 / Chapter 5.2 --- Comparison of Model Prediction --- p.62 / Chapter 5.2.1 --- Misclassification Rate --- p.62 / Chapter 5.2.2 --- Misclassification Rate of Cox's model --- p.63 / Chapter 5.2.3 --- Misclassification Rate of CART model --- p.64 / Chapter 5.2.4 --- Prediction Result --- p.64 / Chapter 6 --- Conclusion --- p.67 / Chapter 6.1 --- Comparison of Results --- p.67 / Chapter 6.2 --- Comparison of the Two Statistical Techniques --- p.68 / Chapter 6.3 --- Limitation --- p.70 / Appendix A: Coding Description for the Health Factors --- p.72 / Appendix B: Log-rank Test --- p.75 / Appendix C: Longitudinal Plot of Time Dependent Variables --- p.76 / Appendix D: Hypothesis Testing of Suspected Covariates --- p.78 / Appendix E: Terminal node report for both gender --- p.81 / Appendix F: Calculation of Critical Values --- p.83 / Appendix G: Distribution of Missing Value in Learning sample and Test Sample --- p.84 / Bibliography --- p.85