This thesis presents a contribution to the active research area of functional data analysis (FDA) and is concerned with the analysis of data from complex experimental designs in which the responses are curves. High resolution, closely correlated data sets are encountered in many research fields, but current statistical methodologies often analyse simplistic summary measures and therefore limit the completeness and accuracy of conclusions drawn. Specifically the nature of the curves and experimental design are not taken into account. Mathematically, such curves can be modelled either as sample paths of a stochastic process or as random elements in a Hilbert space. Despite this more complex type of response, the structure of experiments which yield functional data is often the same as in classical experimentation. Thus, classical experimental design principles and results can be adapted to the FDA setting. More specifically, we are interested in the functional analysis of variance (ANOVA) of experiments which use orthogonal designs. Most of the existing functional ANOVA approaches consider only completely randomised designs. However, we are interested in more complex experimental arrangements such as, for example, split-plot and row-column designs. Similar to univariate responses, such complex designs imply that the response curves for different observational units are correlated. We use the design to derive a functional mixed-effects model and adapt the classical projection approach in order to derive the functional ANOVA. As a main result, we derive new functional F tests for hypotheses about treatment effects in the appropriate strata of the design. The approximate null distribution of these tests is derived by applying the Karhunen- Lo`eve expansion to the covariance functions in the relevant strata. These results extend existing work on functional F tests for completely randomised designs. The methodology developed in the thesis has wide applicability. In particular, we consider novel applications of functional F tests to gait analysis. Results are presented for two empirical studies. In the first study, gait data of patients with cerebral palsy were collected during barefoot walking and walking with ankle-foot orthoses. The effects of ankle-foot orthoses are assessed by functional F tests and compared with pointwise F tests and the traditional univariate repeated-measurements ANOVA. The second study is a designed experiment in which a split-plot design was used to collect gait data from healthy subjects. This is commonly done in gait research in order to better understand, for example, the effects of orthoses while avoiding confounded analysis from the high variability observed in abnormal gait. Moreover, from a technical point of view the study may be regarded as a real-world alternative to simulation studies. By using healthy individuals it is possible to collect data which are in better agreement with the underlying model assumptions. The penultimate chapter of the thesis presents a qualitative study with clinical experts to investigate the utility of gait analysis for the management of cerebral palsy. We explore potential pathways by which the statistical analyses in the thesis might influence patient outcomes. The thesis has six chapters. After describing motivation and introduction in Chapter 1, mathematical representations of functional data are presented in Chapter 2. Chapter 3 considers orthogonal designs in the context of functional data analysis. New functional F tests for complex designs are derived in Chapter 4 and applied in two gait studies. Chapter 5 is devoted to a qualitative study. The thesis concludes with a discussion which details the extent to which the research question has been addressed, the limitations of the work and the degree to which it has been answered.

Made available in DSpace on 2016-04-25T16:44:46Z (GMT). No. of bitstreams: 1 Paulo Renato Marchese Garcia.pdf: 1597436 bytes, checksum: b8aeae0fcbfaf4d72d7899cc1060414d (MD5) Previous issue date: 2015-02-26 / This study aims to empirically test the model of the conditional CAPM in the Brazilian stock market. The analysis is developed through theoretical exposition of the main causes that built the capital asset pricing model and the conditions under which it has been tested and developed. For this purpose, we used a sample of financial assets extracted from Economática system. After that six portfolios were formed based on financial literature assumptions in order to calculate the excess of return in each case. Following the procedure an econometric model was tested and adjusted to be possible its application apply the CAPM conditional version into Brazilian stocks market. Finally, the process was validated given the metrics presented in econometric results being robust and corroborating with the literature / Este trabalho tem por objetivo testar empiricamente o modelo do CAPM condicional no mercado acionário brasileiro. A análise é desenvolvida através da exposição teórica das principais causas que proporcionaram o surgimento do modelo de precificação de ativos financeiros e as condições nas quais ele foi testado e desenvolvido. Para tal, foi utilizada uma amostra de ativos financeiros extraídas do sistema Economática e com base na literatura foram formadas carteiras a fim de calcular o excesso de retorno das composições.Com base em testes econométricos e ajuste da modelagem foi possível aplicar o CAPM condicional no mercado acionário brasileiro e validar sua aplicação uma vez que as métricas apresentadas nos resultados econométricos mostraram-se robustas corroborando com a literatura

Orientador: Vicente Lopes Junior / Banca: Samuel Silva / Banca: Michael John Brennan / Banca: Carlos Alberto Cimini Junior / Resumo: Pesquisadores de diversas partes do mundo se empenham em desenvolver técnicas capazes de monitorar a integridade de máquinas, veículos e estruturas, principalmente as que a ruptura ou destruição possa provocar acidentes e catástrofes. Neste contexto, várias técnicas não destrutivas podem ser utilizadas para monitorar estes sistemas permitindo a realização de reparos e, evitando maiores prejuízos econômicos e danos sociais. A técnica da Impedância Eletromecânica está entre as técnicas baseadas na utilização de materiais piezelétricos e, particularmente, utiliza-se de uma curva sensível a pequenas variações na estrutura, característica que faz a técnica ser eficiente na detecção de danos incipientes. No entanto, sob variações das condições ambiente e de teste, a sensibilidade da técnica pode produzir falsos diagnósticos. Desta forma, o desafio atual é aplicar a técnica da Impedância Eletromecânica em sistemas de monitoramento considerando condições mais próximas às condições de operação reais dos sistemas a serem monitorados. Este trabalho apresenta duas metodologias para sistemas SHM, a primeira consiste em utilizar a técnica de agrupamento Fuzzy c-means para entender e considerar o efeito da temperatura nos sinais da Impedância Eletromecânica. A segunda metodologia utiliza análise de variância (ANOVA) para propor uma metodologia de detecção mais robusta, e assim, incorporar variações aleatórias nos sistemas de medição e aquisição sem comprometer o diagnóstico SHM / Abstract: Researchers around the world are engaged to develop techniques for structural health monitoring of machinery, vehicles and structures, especially systems where damage or destruction could induce accidents and disasters. In this context, several non-destructive techniques can be used to monitor these systems allowing repairs and avoiding major economic losses or social losses. The electromechanical impedance technique is among the techniques based on piezoelectric materials use and it is sensible to small variations in the structure which makes it efficient in detecting incipient damages. However, variations in the ambient or test conditions can cause false diagnoses. Therefore, the current challenge is to apply the electromechanical impedance technique considering monitoring conditions closer to real operating conditions of the systems to be monitored. This work presents two methodologies for SHM systems. The first one uses Fuzzy c-means clustering to distinguish the temperature effect on impedance signal. The second method uses analysis of variance (ANOVA) to propose a more robust detection methodology and thus incorporate random variations in measurement systems and acquisition without loss of SHM diagnostic / Mestre

Philosophiae Doctor - PhD (Industrial Psychology) / Organizations exist for the primary aim of meeting particular objectives: innovation and advancement, customer satisfaction, profit making and delivery of quality goods and services. These goals are mostly channelled with the intent of demonstrating high performance crucial for the continued existence of the organization especially in these rapidly changing global economies. This target, however, cannot be achieved without the aid of employees in the organization. A plethora of previous studies have proven that efficiency, productivity, high performance and stability on the job can be better achieved when the employees are dedicated, committed to their work roles and experience work engagement. The experience of work engagement on the part of the employees is not a random event; it depends on a myriad of factors that include authentic leadership. Leaders have a cumulative change effect on their followers; hence, leaders in an organization can be termed as core drivers of employee engagement. Hence, it becomes imperative to seek to understand what authentic leadership as a construct has to offer to the workplace.

Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering, 1980. / MICROFICHE COPY AVAILABLE IN ARCHIVES AND ENGINEERING. / Includes bibliographical references. / by Bahman Daryanian. / M.S.

A justificativa para o número de animais em experimentos é uma preocupação inerente aos pesquisadores que buscam precisão nos resultados observando as recomendações dos guias de cuidados com animais em pesquisa e ensino. Embora seja do conhecimento de estudiosos a importância do número de repetições, uma vez que o seu aumento resulta em estimativas mais precisas do erro experimental, o seu cálculo no planejamento de experimentos ainda provoca incertezas entre pesquisadores. A determinação do tamanho da amostra também tem fundamental importância nesse contexto, pois a questão que surge é: Aumentar o tamanho da amostra em detrimento do número de repetições ou diminuir o tamanho da amostra favorecendo o aumento no número de repetições? A resposta dependerá da variabilidade dentro da parcela, da variação residual (variância entre parcelas) e dos recursos disponíveis. No presente trabalho, estudou-se a relação entre a variabilidade dentro da parcela e a variância do erro para dados de peso de frangos de corte em experimento completamente casualizado com número diferente de indivíduos por parcela. Tal relação foi confrontada com o número necessário de repetições para detecção de diferenças, entre as médias dos tratamentos, de 5 e 50 gramas, respectivamente, para os 7 e 42 dias. Verificou-se uma grande variabilidade entre os pesos individuais dentro da parcela, provavelmente, consequente da diferença entre as distribuições de pesos dos machos e das fêmeas que se encontravam dentro da mesma parcela no experimento descrito. Constatou-se o baixo poder de teste estatístico para detecção de 5 e 50 gramas, respectivamente, para os 7 e 42 dias e a necessidade de se aumentar o número necessário de repetições, para experimentos similares, no caso em que se queira detectar tais diferenças entre os pesos com poder de teste de, aproximadamente, 0,80 e nível de 5% de significância. / The justification for the number of animals in experiments is an inherent concern for researchers seeking accurate results noting the recommendations of care guides with animals in research and teaching . Although it is known to scholars the importance of the number of replicates, since its increase results in more accurate estimates of experimental error, the calculation in planning experiments still causes uncertainty among researchers. The determination of sample size also has fundamental importance in this context because the question arises: Increasing the sample size rather than the number of replicates or decrease the size of the sample favoring an increase in the number of replicates? The answer will depend on the variability within the plot, the residual variance (variance between plots) and available resources. In this work, we studied the relationship between the variability within the plot and the error variance for data on weight of broilers in a completely randomized experiment with different number of individuals per plot. This relationship was compared to the number of replicates needed to detect differences between the treatment means of 5 and 50 grams, respectively, for 7 and 42 days. There was a large variability between individual weights within the plot, probably resulting from the difference between the distributions of weights of males and females who were in the same plot in the experiment described. It was found low power statistical test for detecting 5 and 50 grams, respectively, for 7 and 42 days and the need to increase the number of replicates required for similar experiments in the case where one wants to detect such differences the weights with the power of approximately 0,80 and the level of significance 5%.

Introdução O consumo alimentar está associado com prevenção ou com risco de doenças e por isso sua estimativa pode ser utilizada como importante fonte de informação para o planejamento de políticas públicas em nutrição. Objetivo Estudar a ingestão habitual de nutrientes em uma amostra representativa de adultos e idosos residentes no município de São Paulo, segundo características sociodemográficas. Métodos Estudo transversal, com amostra representativa da população de adultos e idosos do município de São Paulo, conduzido no ano de 2003 (ISA-2003). Foi coletado um recordatório alimentar de 24 horas (R24h) para cada participante (n=1663), além de dados socioeconômicos e antropométricos. A medida de variabilidade da ingestão foi calculada por meio de duas replicações do R24h em uma subamostra desta população, no ano de 2007 (ISA-2007). A ingestão habitual foi estimada por meio do método desenvolvido pelo Iowa State University no programa PC-SIDE. As prevalências de inadequação foram calculadas pelo método da EAR como ponto de corte, segundo sexo, escolaridade do chefe da família, escolaridade do indivíduo e estado nutricional, posteriormente comparados utilizando o teste de proporções. Foram calculadas as razões de variância intrapessoal sobre a interpessoal entre os sexos. Resultados As prevalências de inadequação mais elevadas foram relativas às vitamina A (67por cento e 58por cento ), vitamina C (52por cento e 62por cento ), tiamina (41por cento e 50por cento ) e riboflavina (29por cento e 19por cento ), para o sexo masculino e feminino, respectivamente. A proporção de indivíduos com ingestão superior ao recomendado de cálcio foi menor que 2por cento e de sódio maior do que 99por cento . A prevalência de inadequação de vitaminas A, C, tiamina, riboflavina e niacina e dos minerais cobre, fósforo e selênio foi mais elevada entre os indivíduos com menor escolaridade, tanto do chefe da família como do indivíduo. Observaram-se diferenças nas frações das variâncias intrapessoais de alguns nutrientes segundo gênero. Conclusão Os adultos e idosos residentes do município de São Paulo apresentaram altas prevalências de inadequação na ingestão das vitaminas A, C, tiamina e riboflavina em ambos os sexos, principalmente entre os com menor escolaridade / Introduction Food intake is associated with prevention or risk of disease and so this estimation can be used as important source of information for planning public policy in nutrition. Objective To study the usual intake of nutrients in a representative sample of adults and older people living in São Paulo, according to sociodemographic characteristics. Methods Cross-sectional study with a representative sample of the adults and older people population in São Paulo, conducted in the year 2003 (ISA-2003). We collected a 24-hour dietary recall (24HR) for each participant (n=1663), and anthropometric and socioeconomic data. The measurement of intake variability was calculated by two replications of 24HR in a subsample of this population in 2007 (ISA-2007). The usual intake was estimated using the PC-SIDE program, which uses the method developed by Iowa State University. The prevalence of inadequacy were calculated by EAR cut-point method, according to sex, education of household head, education and nutritional status of individual, compared using proportion test. Ratios of within- to between-person variation were calculated according to sex. Results The highest prevalence of inadequate intake were related to vitamin A (67per cent and 58per cent ), vitamin C (52per cent and 62per cent ), thiamin (41per cent and 50per cent ) and riboflavin (29per cent and 19per cent ), for male and female, respectively. The proportion of individuals with more than the recommended intake of calcium was less than 2per cent and this percent of sodium was greater than 99per cent . The prevalence of inadequate intake of vitamins A, C, thiamin, riboflavin and niacin and of minerals copper, phosphorus and selenium were higher among individuals with less education, both of the head of the family as the individual. Differences were observed in the ratios of intraindividual variances of some nutrients by sex. Conclusion Adults and older people living in São Paulo presented high prevalence of inadequate intake of vitamins A, C, thiamin and riboflavin for both sexes, especially among the less educated people

É muito comum encontrar nas áreas agronômica e biológica experimentos cujas observações são correlacionadas. Porém, tais correlações, em tese, podem estar associadas às parcelas ou às subparcelas, dependendo do plano experimental adotado. Além disso, a metodologia de modelos lineares mistos vem sendo utilizada com mais freqüência, principalmente após os trabalhos de Searle (1988), Searle at al. (1992), Wolfinger (1993b) entre outros. O sucesso do procedimento de modelagem está fortemente associado ao exame dos efeitos aleatórios que devem permanecer no modelo e na possibilidade de se introduzir, no modelo, estruturas de variâncias e covariâncias das variáveis aleatórias que, para o modelo linear misto, podem estar inseridas no resíduo e, também, na parte aleatória associada ao fator aleatório conhecido. Nesse contexto, o Teste da Razão de Verossimilhança e o Critério de Akaike podem auxiliar na tarefa de escolha do modelo mais apropriado para análise dos dados, além de permitir verificar que escolhas de modelos inadequadas acarretam em conclusões divergentes em relação aos efeitos fixos do modelo. Com o desenvolvimento do Proc Mixed do SAS (Littel at al. 1996), utilizado neste trabalho, a análise desses experimentos, tratada pela metodologia modelos lineares mistos, tornou-se mais usual e segura. Com a finalidade de se atingir o objetivo deste trabalho, utilizaram-se dois exemplos (A e B) sobre a resposta da produtividade de três cultivares de trigo, em relação a níveis de irrigação por aspersão line-source. Foram criados e analisados 29 modelos para o Exemplo A e 16 modelos para o Exemplo B. Pôde-se verificar, para cada um dos exemplos, que as conclusões em relação aos efeitos fixos se modificaram de acordo com o modelo adotado. Notou-se, também, que o Critério de Akaike deve ser visto com cautela. Ao se comparar modelos similares entre os dois exemplos, ratificou-se a importância de se programar corretamente no Proc Mixed. Nesse contexto, conclui-se que é fundamental conduzir a análise de experimentos de forma ampla, buscando vários modelos e verificando quais têm lógica em relação ao plano experimental, evitando erros ao término da análise. / In Biology and Agronomy, experiments that produce correlated observations are often found. Theoretically, these correlations may be associated with whole-plots or subplots, according to the chosen experimental design. Also, the mixed linear model methodology is now being used much more frequently, especially after the works of Searle (1988), Searle et al. (1992) and Wolfinger (1993b), among others. The success of the modeling procedure is strongly associated with the examination of the random effects that must remain within the model and the possibility of introducing variance-covariance structures of random variables in the model. In the case of the mixed linear model, they may be included in the residual error or in the random part which is associated with the known random factor. In this context, the Likelihood Ratio Test and Akaike's Information Criterion can help in choosing the most appropriate model for data analysis. They also enable the verification of inadequate choice of models which can lead to divergent conclusions regarding the fixed effects of the model. With the development of the SAS Mixed Procedure (Little at al. 1996), which was used in this work, analysis of these experiments, conducted through the mixed linear model methodology, has become more usual and secure. In order to achieve the target of this work, two examples were utilized (A and B) involving the productivity response of three varieties of wheat, in regards to irrigation levels by line-source aspersion. Twenty-nine models for Example A and 16 models for Example B were created and analyzed. For each example, it was verified that conclusions regarding fixed effects changed according to the model adopted. It was also verified that Akaike’s Information Criterion must be regarded with caution. When comparing similar models between the two examples, the importance of correct programming in the Mixed Procedure was confirmed. In this context, it can be concluded that it is fundamental to conduct the experiment analysis in an ample manner, looking for various models and verifying which ones make sense according to the experimental plan, thus avoiding errors at analysis completion.

This thesis deals with the estimation of unobserved variables or states from a time series of noisy observations. Approximate minimum variance filters for a class of discrete time systems with both additive and multiplicative noise, where the measurement might be delayed randomly by one or more sample times, are investigated. The delayed observations are modelled by up to N sample times by using N Bernoulli random variables with values of 0 or 1. We seek to minimize variance over a class of filters which are linear in the current measurement (although potentially nonlinear in past measurements) and present a closed-form solution. An interpretation of the multiplicative noise in both transition and measurement equations in terms of filtering under additive noise and stochastic perturbations in the parameters of the state space system is also provided. This filtering algorithm extends to the case when the system has continuous time state dynamics and discrete time state measurements. The Euler scheme is used to transform the process into a discrete time state space system in which the state dynamics have a smaller sampling time than the measurement sampling time. The number of sample times by which the observation is delayed is considered to be uncertain and a fraction of the measurement sample time. The same problem is considered for nonlinear state space models of discrete time systems, where the measurement might be delayed randomly by one sample time. The linearisation error is modelled as an additional source of noise which is multiplicative in nature. The algorithms developed are demonstrated throughout with simulated examples.

This thesis consists of one stock return predictability study and two international risk exposure studies. The first study shows that the statistical significance of out-of-sample predictability of market returns given by Kelly and Pruitt (2013), using a partial least squares methodology, constructed from the valuation ratios of portfolios, is overstated for two reasons. Firstly, the analysis is conducted on gross returns rather than excess returns, and this raises the apparent predictability of the equity premium due to the inclusion of predictable movements of interest rates. Secondly, the bootstrap statistics used to assess out-of-sample significance do not account for small-sample bias in the estimated coefficients. This bias is well known to affect in-sample tests of significance and I show that it is also important for out-of-sample tests of significance. Accounting for both these effects can radically change the conclusions; for example, the recursive out-of-sample R2 values for the sample period 1965-2010 are insignificant for the prediction of one-year excess returns, and one-month returns, except in the case of the book-to-market ratios of six size- and value-sorted portfolios which are significant at the 10% level. The second study examines whether U.S. common stocks are exposed to international risks, which I define as shocks to foreign markets that are orthogonal to U.S. market returns. By sorting stocks on past exposure to this risk factor I show that it is possible to create portfolios with an ex-post spread in exposure to international risk. I examine whether the international risk is priced in the cross-section of U.S. stocks, and find that for small stocks an increase in exposure to international risk results in lower returns relative to the Fama-French three-factor model. I conduct similar analysis on a measure of the international value premium and find little evidence of this risk being priced in U.S. stocks. The third study examines whether a portfolios of U.S. stocks can mimic foreign index returns, thereby providing investors with the benefits of international diversification without the need to invest directly in assets that trade abroad. I test this proposition using index data from seven developed markets and eight emerging markets over the period 1975-2013. Portfolios of U.S. stocks are constructed out-of-sample to mimic these international indices using a step-wise procedure that selects from a variety of industry portfolios, stocks of multinational corporations, country funds and American depositary receipts. I also use a partial least squares approach to form mimicking portfolios. I show that investors are able to gain considerable exposure to emerging market indices using domestically traded stocks. However, for developed market indices it is difficult to obtain home-made exposure beyond the simple exposure of foreign indices to the U.S. market factor. Using mean-variance spanning tests I find that, with few exceptions, international indices do not improve over the investment frontier provided by the domestically constructed alternative of investing in the U.S. market index and portfolios of industries and multinational corporations.