This century is surely the century of data (Donoho, 2000). Data analysis has been an emerging activity over the last few decades. High dimensional data is in particular more and more pervasive with the advance of massive data collection system, such as microarrays, satellite imagery, and financial data. However, analysis of high dimensional data is of challenge with the so called curse of dimensionality (Bellman 1961). This research dissertation presents several methodologies in the application of high dimensional data analysis. The first part discusses a joint analysis of multiple microarray gene expressions. Microarray analysis dates back to Golub et al. (1999). It draws much attention after that. One common goal of microarray analysis is to determine which genes are differentially expressed. These genes behave significantly differently between groups of individuals. However, in microarray analysis, there are thousands of genes but few arrays (samples, individuals) and thus relatively low reproducibility remains. It is natural to consider joint analyses that could combine microarrays from different experiments effectively in order to achieve improved accuracy. In particular, we present a model-based approach for better identification of differentially expressed genes by incorporating data from different studies. The model can accommodate in a seamless fashion a wide range of studies including those performed at different platforms, and/or under different but overlapping biological conditions. Model-based inferences can be done in an empirical Bayes fashion. Because of the information sharing among studies, the joint analysis dramatically improves inferences based on individual analysis. Simulation studies and real data examples are presented to demonstrate the effectiveness of the proposed approach under a variety of complications that often arise in practice. The second part is about covariance matrix estimation in high dimensional data. First, we propose a penalised likelihood estimator for high dimensional t-distribution. The student t-distribution is of increasing interest in mathematical finance, education and many other applications. However, the application in t-distribution is limited by the difficulty in the parameter estimation of the covariance matrix for high dimensional data. We show that by imposing LASSO penalty on the Cholesky factors of the covariance matrix, EM algorithm can efficiently compute the estimator and it performs much better than other popular estimators. Secondly, we propose an estimator for high dimensional Gaussian mixture models. Finite Gaussian mixture models are widely used in statistics thanks to its great flexibility. However, parameter estimation for Gaussian mixture models with high dimensionality can be rather challenging because of the huge number of parameters that need to be estimated. For such purposes, we propose a penalized likelihood estimator to specifically address such difficulties. The LASSO penalty we impose on the inverse covariance matrices encourages sparsity on its entries and therefore helps reducing the dimensionality of the problem. We show that the proposed estimator can be efficiently computed via an Expectation-Maximization algorithm. To illustrate the practical merits of the proposed method, we consider its application in model-based clustering and mixture discriminant analysis. Numerical experiments with both simulated and real data show that the new method is a valuable tool in handling high dimensional data. Finally, we present structured estimators for high dimensional Gaussian mixture models. The graphical representation of every cluster in Gaussian mixture models may have the same or similar structure, which is an important feature in many applications, such as image processing, speech recognition and gene network analysis. Failure to consider the sharing structure would deteriorate the estimation accuracy. To address such issues, we propose two structured estimators, hierarchical Lasso estimator and group Lasso estimator. An EM algorithm can be applied to conveniently solve the estimation problem. We show that when clusters share similar structures, the proposed estimator perform much better than the separate Lasso estimator.

Background: Community-acquired pneumonia (CAP) is an acute disease condition with a high risk of rapid deteriorations. We analysed the influence of genetics on cytokine regulation to obtain a better understanding of patient’s heterogeneity. Methods: For up to N = 389 genotyped participants of the PROGRESS study of hospitalised CAP patients, we performed a genome-wide association study of ten cytokines IL-1β, IL-6, IL-8, IL-10, IL-12, MCP-1 (MCAF), MIP-1α (CCL3), VEGF, VCAM-1, and ICAM-1. Consecutive secondary analyses were performed to identify independent hits and corresponding causal variants. Results: 102 SNPs from 14 loci showed genome-wide significant associations with five of the cytokines. The most interesting associations were found at 6p21.1 for VEGF (p = 1.58 × 10−20), at 17q21.32 (p = 1.51 × 10−9) and at 10p12.1 (p = 2.76 × 10−9) for IL-1β, at 10p13 for MIP-1α (CCL3) (p = 2.28 × 10−9), and at 9q34.12 for IL-10 (p = 4.52 × 10−8). Functionally plausible genes could be assigned to the majority of loci including genes involved in cytokine secretion, granulocyte function, and cilial kinetics. Conclusion: This is the first context-specific genetic association study of blood cytokine concentrations in CAP patients revealing numerous biologically plausible candidate genes. Two of the loci were also associated with atherosclerosis with probable common or consecutive pathomechanisms.

As a valuable asset in human augmentation and medical rehabilitation, exoskeletons have become a major area for research and development. They have shown themselves to be effective tools for training and rehabilitation of individuals suffering from limited mobility. However, most exoskeletons are not capable of balancing without the assistance of crutches from the user. Leveraging technology and techniques developed for force controlled humanoid robots, a project was undertaken to develop a fully self-balancing, compliant lower-body robotic exoskeleton. Due to their many beneficial features, series elastic actuators were utilized to power the joints on the exoskeleton. This thesis details the development of four linear series elastic actuators (LSEA) as part of this project. All 12-degrees of freedom will be powered by one of these four LSEA's. Actuator requirements were developed by examining human gait data and three robot-walking simulations. These four walking scenarios were synthesized into one set of power requirements for actuator development. Using these requirements, analytical models were developed to perform component trade studies and predict the performance of the actuator. These actuators utilize high-efficacy components, parallel electric motors, and liquid cooling to attain high power-to-weight ratios, while maintaining a small lightweight design. These analyses and trade studies have resulted in the design of a dual-motor liquid-cooled actuator capable of producing a peak force 8500N with a maximum travel speed of 0.267m/s, and three different single-motor actuators capable of producing forces up to 2450N continuously, with a maximum travel speeds up to 0.767m/s. / Master of Science / Patients who suffer a severe back injury that results in paralysis from the waist down (paraplegia) commonly regain mobility in their daily lives by using a wheelchair. However, staying in a seated position for long periods can cause serious medical issues to arise. In order to address these issues, lower-body exoskeletons have been developed to help patients walk again. Exoskeletons are mechanical devices a person can wear to enhance their physical strength or endurance beyond their normal capability. These exoskeletons have shown themselves to be effective tools for training and rehabilitation of individuals suffering from limited mobility. However, most exoskeletons are not capable of balancing the user while they walk. In order to maintain balance, the user must hold themselves up with crutches. As with a wheelchair, heavy dependence on crutches can lead to new medical issues for the patient. To solve this problem, technology and techniques created for humanoid robots were used to develop a fully self-balancing exoskeleton. This exoskeleton is known as the Orthotic Lower-body Locomotion Exoskeleton. This thesis details the development of four actuators to power all twelve joints of the exoskeleton. These actuators utilize high-efficiency components, multiple electric motors, and liquid cooling to maintain a small lightweight design and while obtaining very high-power outputs.

本研究共壹冊，預計四萬至六萬字，分六章：第一章、導論，第二節、參考文獻與研 究架構，第三章、研究設計，第四章、第一階段研究之結果，第五章、第二階段研究 之結果，第六章、結論與建議。以往台灣的醫院多半不重視顧客導向，所以民眾對醫 院的服務常常感到不滿意。本研究目的即是要利用聯合分析找出民眾選擇醫院所考慮 的因素及其水準。聯合分析是一種相依的多變量分析技術，它主要的目的是：探討分 析預測變數各水準對準則變數之貢獻，在本研究指的是醫院各屬性水準對顧客偏好大 小的影響。本研究採便利抽權，以人員訪問方式接觸受測者，並以問卷為工具來收集 初級資料。除聯合分析外，同時使用Thurstone′s Case V 抽取變數，多元尺度法描 繪產品及理想聯合空間圖，找出最接近理想的醫院。

O objetivo deste trabalho foi avaliar a incorporação de funções geoestatísticas na matriz de variâncias e covariâncias residual no estudo de modelos lineares mistos a partir de um grupo de quatro experimentos de cana-de-açúcar, conduzidos na Guatemala nos seguintes locais: fazenda Limones - usina açucareira Pantaleón (LP), fazenda Bálsamo - usina açucareira Pantaleón (BP), área 1 da fazenda Limones - usina Madre Tierra (MT1) e área 2 da fazenda Limones - usina Madre Tierra (MT2). A variável resposta de interesse foi a produção de cana-de-açúcar por hectare, o delineamento utilizado nos quatro locais foi o casualizado em blocos, com cinco repetições e os mesmos seis tratamentos referentes a diferentes dosagens de um biorregulador (estimulante de crescimento). Em princípio, foram ajustados e comparados diversos modelos alternando-se o efeito de blocos, ora considerado fixo, ora aleatório, e a estrutura da matriz de variâncias e covariâncias (R), segundo os modelos exponencial, gaussiano e esférico. Estes modelos foram comparados, e os que admitem estruturas de dependência espacial se destacaram estatisticamente como os melhores, a partir do critério de Akaike (AIC), sendo então selecionados os modelos BFExp (blocos de efeito fixo e função exponencial na matriz R) e BAExpH (blocos de efeito aleatório, função exponencial para R e variâncias diferentes entre os locais). A seguir, foi realizada a estimação dos efeitos fixos e a predição dos efeitos aleatórios por meio do método da máxima verossimilhança restrita (REML) pois esta metodologia proporciona um menor viés para suas estimativas. As análises conjuntas nos dois modelos selecionados não apresentaram interação tratamentos versus locais, nem mesmo efeito de tratamentos significativos, não sendo aconselhado o desdobramento desta interação. O efeito de locais por sua vez, foi significativo apenas no modelo BAExpH, e detectou-se neste caso a superioridade do local BP em relação aos demais. Adicionalmente, os locais foram analisados individualmente, focando a comparação dos modelos e as análises de variâncias, contudo, assim como na análise conjunta, nos modelos escolhidos para cada local, os efeitos de tratamentos também não foram significativos. Gráficos de resíduos foram construídos e representaram bons ajustes para os modelos BFExp e BAExpH para descrever os dados deste grupo de experimentos. Por fim, foi realizado um estudo de simulação cujos resultados deram mais credibilidade e suporte para a importância e relevância de se verificar, por meio de comparações, a necessidade de uso de um modelo mais elaborado, que considere a possível existência de dependência espacial entre as observações. / The aim of this research was to evaluate the incorporation of geostatistical functions in the residual variances and covariances matrix in linear mixed models in a group of four experiments cane sugar conducted in four sites of Guatemala: farm Limones - Pantaleon sugar mill (LP), farm Bálsamo - Pantaleon sugar mill (BP), area 1 of the farm Limones - sugar mill Madre Tierra (MT1) and area 2 of the farm Limones - sugar mill Madre Tierra (MT2). Production of sugar cane was the interest variable analyzed at all locations, using the randomized block design with five replications and the same six treatments related to different doses of a plant growth regulator. Initially the models were adjusted and compared with alternating the blocks effect, sometimes considered fixed, sometimes random, and the structure of the variance and covariance matrix (R) according to the exponential, gaussian and spherical models. The models were compared, and, among them, those with spatial dependence structures stood out as the best statistically from the Akaike information criterion (AIC), and the selected modelos were the BFExp model (block as fixed effect and exponential function to R) and the BAExpH model (block as random effect, exponential function to R and different variances among the sites). After that, the estimation of fixed effects and prediction of random effects using the restricted maximum likelihood method (REML) were done, since this methodology provides a lower bias to their estimates. The joint analysis of both selected models showed no interaction between treatments and locals, even significant effect of treatments, not being advised the unfolding of this interaction. The effect of local was significant only in the BAExpH model, and detected in this case the superiority of the local BP in relation to the others. Additionally, individual sites were examined similarly to the previous case, through comparison of models and analysis of variance, however, treatment effects weren\'t significant too. Residual plots were constructed and represented satisfactory fit of the models to describe the data in all cases studied. Finally, a simulation study showed results with more credibility and support for the importance and relevance of verifying, through comparisons, the need to use a more structured model that considers the possible existence of spatial dependence among observations.

Made available in DSpace on 2009-11-18T19:00:49Z (GMT). No. of bitstreams: 1 ACF155.pdf: 526538 bytes, checksum: be4ca3ee68364433f3fecaac30bb476d (MD5) Previous issue date: 2007 / The general objective of this research is to verify which attributes are most relevant to a stock photography agency that represent the purchaser's standards of choice. For this objective to be accomplished, qualitative interviews with the customers of stock photography agencies had been made in order to raise the attributes considered with relevance in the process of choice for the Brazilian stock photography agency market. The levels of each attribute to be tested had arisen through the mapping of the products and services offered by the competition and the relative weight assigned to each one of the attributes related to the research in the choices for a stock photography agency. A transversal study was made with a sample of stock photography agencies customers from Brazil¿s Southeastern region. For the analysis of this data, a survey method was used, that, according to MALHOTRA (2006: 182), involves a structuralized questionnaire to be answered by an interview that elucidates specific information, in which the questions had a predetermined order. This questionnaire was presented through interviews on the Internet. The method adopted for this analysis was a joint analysis. A sampling of 1000 customer stock photography agencies were selected, which were represented by a didactic book editor, advertising agencies, editorial companies, etc., in the states of Rio de Janeiro, São Paulo, Espírito Santo and Minas Gerais. They had been obtained by 16 stimulations, or cards, for the application of the companies. Of the sample of 1000 customers of stock photography agencies, 7,8% responded to the research. The attribute most relevant in accordance with the presented results is the availability of images in high resolution for layout. Its relative importance was 40,78%. At the end of the study, the management implications were propitiated to the stock photography agencies managers inabling them to be more competitive. / O objetivo geral desta pesquisa é verificar quais são os atributos mais relevantes de um banco de imagens que representem os padrões de escolha dos compradores deste mercado. Para que tal objetivo fosse alcançado, foram realizadas entrevistas qualitativas com os clientes de banco de imagens a fim de levantar os atributos considerados relevantes no processo de escolha do mesmo dentre os bancos de imagens existentes no mercado brasileiro. Levantaram-se os níveis de cada atributo a ser testado, através do mapeamento dos produtos e serviços ofertados pela concorrência, e estimou-se o peso relativo a cada um dos atributos relacionados na pesquisa na escolha de um banco de imagem. Realizou-se uma pesquisa descritiva, um estudo transversal único de onde foi extraída de uma população de clientes de bancos de imagem no Brasil uma amostra de clientes de banco de imagem da região Sudeste. Para a análise destes dados, utilizou-se o método de levantamento, que, segundo MALHOTRA (2006:182), envolve um questionário estruturado a ser respondido pelos entrevistados que elucida informações específicas, no qual as perguntas possuíam uma ordem predeterminada. Este questionário foi apresentado através de entrevistas pela Internet. O método adotado para a análise dos dados foi análise conjunta. Para este estudo foi selecionada uma amostra de 1000 clientes de bancos de imagens, que são representados por agências de publicidade, editoras de livros didáticos, empresas de editoriais etc, nos estados do Rio de Janeiro, São Paulo, Espírito Santo e Minas Gerais, e foram obtidos 16 estímulos ou cartões para a aplicação junto às empresas. Da amostra de 1000 clientes de bancos de imagem, 7,8% responderam à pesquisa. Através desta pesquisa verificou-se que o atributo mais relevante foi a disponibilidade de imagens em alta resolução para layout. Sua importância relativa foi de 40,78%. No final do estudo, as implicações gerenciais propiciaram aos tomadores de decisão de bancos de imagens fatores que poderão torná-los mais competitivos.

O objetivo deste trabalho foi avaliar a incorporação de funções geoestatísticas na matriz de variâncias e covariâncias residual no estudo de modelos lineares mistos a partir de um grupo de quatro experimentos de cana-de-açúcar, conduzidos na Guatemala nos seguintes locais: fazenda Limones - usina açucareira Pantaleón (LP), fazenda Bálsamo - usina açucareira Pantaleón (BP), área 1 da fazenda Limones - usina Madre Tierra (MT1) e área 2 da fazenda Limones - usina Madre Tierra (MT2). A variável resposta de interesse foi a produção de cana-de-açúcar por hectare, o delineamento utilizado nos quatro locais foi o casualizado em blocos, com cinco repetições e os mesmos seis tratamentos referentes a diferentes dosagens de um biorregulador (estimulante de crescimento). Em princípio, foram ajustados e comparados diversos modelos alternando-se o efeito de blocos, ora considerado fixo, ora aleatório, e a estrutura da matriz de variâncias e covariâncias (R), segundo os modelos exponencial, gaussiano e esférico. Estes modelos foram comparados, e os que admitem estruturas de dependência espacial se destacaram estatisticamente como os melhores, a partir do critério de Akaike (AIC), sendo então selecionados os modelos BFExp (blocos de efeito fixo e função exponencial na matriz R) e BAExpH (blocos de efeito aleatório, função exponencial para R e variâncias diferentes entre os locais). A seguir, foi realizada a estimação dos efeitos fixos e a predição dos efeitos aleatórios por meio do método da máxima verossimilhança restrita (REML) pois esta metodologia proporciona um menor viés para suas estimativas. As análises conjuntas nos dois modelos selecionados não apresentaram interação tratamentos versus locais, nem mesmo efeito de tratamentos significativos, não sendo aconselhado o desdobramento desta interação. O efeito de locais por sua vez, foi significativo apenas no modelo BAExpH, e detectou-se neste caso a superioridade do local BP em relação aos demais. Adicionalmente, os locais foram analisados individualmente, focando a comparação dos modelos e as análises de variâncias, contudo, assim como na análise conjunta, nos modelos escolhidos para cada local, os efeitos de tratamentos também não foram significativos. Gráficos de resíduos foram construídos e representaram bons ajustes para os modelos BFExp e BAExpH para descrever os dados deste grupo de experimentos. Por fim, foi realizado um estudo de simulação cujos resultados deram mais credibilidade e suporte para a importância e relevância de se verificar, por meio de comparações, a necessidade de uso de um modelo mais elaborado, que considere a possível existência de dependência espacial entre as observações. / The aim of this research was to evaluate the incorporation of geostatistical functions in the residual variances and covariances matrix in linear mixed models in a group of four experiments cane sugar conducted in four sites of Guatemala: farm Limones - Pantaleon sugar mill (LP), farm Bálsamo - Pantaleon sugar mill (BP), area 1 of the farm Limones - sugar mill Madre Tierra (MT1) and area 2 of the farm Limones - sugar mill Madre Tierra (MT2). Production of sugar cane was the interest variable analyzed at all locations, using the randomized block design with five replications and the same six treatments related to different doses of a plant growth regulator. Initially the models were adjusted and compared with alternating the blocks effect, sometimes considered fixed, sometimes random, and the structure of the variance and covariance matrix (R) according to the exponential, gaussian and spherical models. The models were compared, and, among them, those with spatial dependence structures stood out as the best statistically from the Akaike information criterion (AIC), and the selected modelos were the BFExp model (block as fixed effect and exponential function to R) and the BAExpH model (block as random effect, exponential function to R and different variances among the sites). After that, the estimation of fixed effects and prediction of random effects using the restricted maximum likelihood method (REML) were done, since this methodology provides a lower bias to their estimates. The joint analysis of both selected models showed no interaction between treatments and locals, even significant effect of treatments, not being advised the unfolding of this interaction. The effect of local was significant only in the BAExpH model, and detected in this case the superiority of the local BP in relation to the others. Additionally, individual sites were examined similarly to the previous case, through comparison of models and analysis of variance, however, treatment effects weren\'t significant too. Residual plots were constructed and represented satisfactory fit of the models to describe the data in all cases studied. Finally, a simulation study showed results with more credibility and support for the importance and relevance of verifying, through comparisons, the need to use a more structured model that considers the possible existence of spatial dependence among observations.

Made available in DSpace on 2015-04-11T13:54:52Z (GMT). No. of bitstreams: 1 Dissertacao-Jose Lucio do Nascimento Rabelo.pdf: 6377803 bytes, checksum: d176288411511a233eb2e3bcac3bfe35 (MD5) Previous issue date: 2009-02-27 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / This objective work to define ambient attributes of the narrow river of Mestre Chico to subsidize studies of economic valuation, mainly those that use the technique of Declared Preference. The results reached here for the narrow river of Mestre Chico will be able to guide the formularization and implementation of ambient politics and to awake the interest of the society for its restoration and preservation. Two methods of valuation are applicable in this context where if it looks for esteem unrelated value to the use of ambient attributes - contingent valuation and joint analysis. This last one was chosen because it carries through the valuation study analyzing a set of characteristics of an ambient good, while the other value in function of a scale of monetary values previously established and submitted to the interviewed ones. The method of Joint Analysis is a used tool esteem the relative importance that the interviewed ones confer the definitive attributes of goods and services and the utilities associates to these attributes. For its application it has the necessity of the definition of attributes and its levels, that in this work had been selected by the technique of Group of Focus. The election process was complemented by means of interviews with specialists and for consultation the secondary sources. This method allows to the public manager the use of a tool capable to evaluate the preference of the population how much the diverse attributes of projects, programs and public politics. To the end of this work an excellent set of attributes and levels was selected. This will allow the organization of alternatives - a combination of diverse attributes, that applied in the methodology of Joint Analysis, will be capable to catch the declared value of interviewed in relation to the recovery and the maintenance of the ambient quality of the Narrow river of Mestre Chico or other similar courses of water. / Este trabalho objetiva definir atributos ambientais do igarapé do Mestre Chico em Manaus- AM para subsidiar estudos de valoração econômica, principalmente aqueles que utilizam a técnica de Preferência Declarada. Os resultados aqui alcançados para o igarapé do Mestre Chico poderão orientar a formulação e implementação de políticas ambientais e despertar o interesse da sociedade para a sua restauração e preservação. Dois métodos de valoração são aplicáveis neste contexto onde se procura estimar valor não relacionado ao uso de atributos ambientais valoração contingente e análise conjunta. Este último foi escolhido porque realiza o estudo de valoração analisando um conjunto de características de um bem ambiental, enquanto o outro valora em função de uma escala de valores monetários previamente estabelecidos e submetidos aos entrevistados. O método de Análise Conjunta é uma ferramenta usada para estimar a importância relativa que os entrevistados conferem a determinados atributos de bens e serviços e as utilidades associadas a estes atributos. Para a sua aplicação há a necessidade da definição de atributos e seus níveis, que neste trabalho foram selecionados pela técnica de Grupo de Foco. O processo de seleção foi complementado por meio de entrevistas com especialistas e por consulta a fontes secundárias. Este método permite ao gestor público o uso de uma ferramenta capaz de avaliar a preferência da população quanto a diversos atributos de projetos, programas e políticas públicas. Ao final deste trabalho um conjunto relevante de atributos e níveis foi selecionado. Isto permitirá a organização de alternativas - uma combinação de diversos atributos, que aplicadas na metodologia de Análise Conjunta, serão capazes de captar o valor declarado dos entrevistados em relação à recuperação e manutenção da qualidade ambiental do Igarapé do Mestre Chico ou de outros cursos d água semelhantes.

Este trabalho objetivou a avaliação da presença de plasticidade fenotípica e de adaptação local de três procedências de palmiteiro: Ombrófila Densa, Estacional Semidecidual e Restinga, em três locais no Estado de São Paulo: Parque Estadual da Ilha do Cardoso, Parque Estadual de Carlos Botelho e Estação Ecológica dos Caetetus, em ensaios de adaptação no estabelecimento (ou de semeadura) e de adaptação em juvenis (ou de crescimento). Os conjuntos de dados foram analisados utilizando estruturas de grupos de experimentos, com efeitos cruzados e aninhados. As variáveis relacionadas com a massa de matéria seca das plantas, nos dois ensaios, foram analisadas usando a abordagem de modelos lineares de efeitos mistos, por meio da incorporação de fatores de efeito aleatório, e fazendo uso do método da máxima verossimilhança restrita (REML) para estimação dos componentes de variância associados a tais fatores com um menor viés. Por outro lado, para a proporção de sementes germinadas, no ensaio de adaptação no estabelecimento, a análise estatística foi realizada a partir da abordagem dos modelos lineares generalizados mistos, sob a pressuposição de que a variável segue uma distribuição binomial, com função de ligação logito. O método da pseudo-verossimilhança foi empregado para obtenção da solução das equações de verossimilhança. Os resultados mostraram que as plantas originadas de sementes dos três biomas avaliados apresentaram um comportamento plástico, para todos os caracteres avaliados no ensaio de adaptação no estabelecimento. Com relação ao ensaio de adaptação em juvenis, a característica de plasticidade foi verificada somente para a massa de matéria seca da folha em plantas provenientes do bioma Estacional Semidecidual. A característica de adaptação local, apresentou-se de forma evidente no ensaio de adaptação no estabelecimento. Estes resultados evidenciaram que em cada local avaliado, as plantas originadas das sementes de diferentes procedências apresentaram um comportamento diferenciado nos caracteres relacionados à massa de matéria seca, podendo em alguns casos, tratar-se de adaptação local. Concluiu-se que os locais Carlos Botelho e Ilha do Cardoso são os mais favoráveis para a germinação das sementes de sua mesma procedência. / The aim of this work was to evaluate the presence of phenotypic plasticity and local adaptation of three provenances of the palm specie Euterpe edulis: Atlantic Rainforest, Seasonally Dry Forest and Restinga Forest, in permanent parcels inserted in three forest types of the São Paulo State (Brazil): Parque Estadual da Ilha do Cardoso, Parque Estadual de Carlos Botelho e Estação Ecológica dos Caetetus, in experiments of seedling establishment and juveniles plants growth. The data sets were analyzed using structures of groups of experiments, with crossed and nested effects. The variables related to dry matter content of plants in both assays were analyzed using linear mixed models (LMM) approach, through the incorporation of random effect factors, and using the restricted maximum likelihood method (REML) for estimation of variance components associated with these factors with a minor bias. On the other hand, germination proportion of the seeds at seedling establishment assay was analyzed using the generalized linear mixed models (GLMM) approach, under the assumption that the variable follows a binomial distribution, with logit link function. The pseudo-likelihood (PL) method was used to obtain the numerical solution of the likelihood equations. The results showed that, plants from seeds of the three biomes evaluated presented a plastic behavior for all characters assessed in the seedling establishment assay. In respect to juveniles adaptation assay, the phenotypic plasticity characteristic was observed only to the leaf dry matter content of plants from Seasonally Dry Forest biome. The local adaptation characteristic was clearly observed in the seedling establishment assay. These results showed that at each site evaluated, plants originating from seeds of different provenances exhibited different behavior on characters related to the dry matter content and may in some cases be local adaptation. It was concluded that locations Carlos Botelho and Ilha do Cardoso are the most favorable for seed germination of its same provenance.

Este trabalho objetivou a avaliação da presença de plasticidade fenotípica e de adaptação local de três procedências de palmiteiro: Ombrófila Densa, Estacional Semidecidual e Restinga, em três locais no Estado de São Paulo: Parque Estadual da Ilha do Cardoso, Parque Estadual de Carlos Botelho e Estação Ecológica dos Caetetus, em ensaios de adaptação no estabelecimento (ou de semeadura) e de adaptação em juvenis (ou de crescimento). Os conjuntos de dados foram analisados utilizando estruturas de grupos de experimentos, com efeitos cruzados e aninhados. As variáveis relacionadas com a massa de matéria seca das plantas, nos dois ensaios, foram analisadas usando a abordagem de modelos lineares de efeitos mistos, por meio da incorporação de fatores de efeito aleatório, e fazendo uso do método da máxima verossimilhança restrita (REML) para estimação dos componentes de variância associados a tais fatores com um menor viés. Por outro lado, para a proporção de sementes germinadas, no ensaio de adaptação no estabelecimento, a análise estatística foi realizada a partir da abordagem dos modelos lineares generalizados mistos, sob a pressuposição de que a variável segue uma distribuição binomial, com função de ligação logito. O método da pseudo-verossimilhança foi empregado para obtenção da solução das equações de verossimilhança. Os resultados mostraram que as plantas originadas de sementes dos três biomas avaliados apresentaram um comportamento plástico, para todos os caracteres avaliados no ensaio de adaptação no estabelecimento. Com relação ao ensaio de adaptação em juvenis, a característica de plasticidade foi verificada somente para a massa de matéria seca da folha em plantas provenientes do bioma Estacional Semidecidual. A característica de adaptação local, apresentou-se de forma evidente no ensaio de adaptação no estabelecimento. Estes resultados evidenciaram que em cada local avaliado, as plantas originadas das sementes de diferentes procedências apresentaram um comportamento diferenciado nos caracteres relacionados à massa de matéria seca, podendo em alguns casos, tratar-se de adaptação local. Concluiu-se que os locais Carlos Botelho e Ilha do Cardoso são os mais favoráveis para a germinação das sementes de sua mesma procedência. / The aim of this work was to evaluate the presence of phenotypic plasticity and local adaptation of three provenances of the palm specie Euterpe edulis: Atlantic Rainforest, Seasonally Dry Forest and Restinga Forest, in permanent parcels inserted in three forest types of the São Paulo State (Brazil): Parque Estadual da Ilha do Cardoso, Parque Estadual de Carlos Botelho e Estação Ecológica dos Caetetus, in experiments of seedling establishment and juveniles plants growth. The data sets were analyzed using structures of groups of experiments, with crossed and nested effects. The variables related to dry matter content of plants in both assays were analyzed using linear mixed models (LMM) approach, through the incorporation of random effect factors, and using the restricted maximum likelihood method (REML) for estimation of variance components associated with these factors with a minor bias. On the other hand, germination proportion of the seeds at seedling establishment assay was analyzed using the generalized linear mixed models (GLMM) approach, under the assumption that the variable follows a binomial distribution, with logit link function. The pseudo-likelihood (PL) method was used to obtain the numerical solution of the likelihood equations. The results showed that, plants from seeds of the three biomes evaluated presented a plastic behavior for all characters assessed in the seedling establishment assay. In respect to juveniles adaptation assay, the phenotypic plasticity characteristic was observed only to the leaf dry matter content of plants from Seasonally Dry Forest biome. The local adaptation characteristic was clearly observed in the seedling establishment assay. These results showed that at each site evaluated, plants originating from seeds of different provenances exhibited different behavior on characters related to the dry matter content and may in some cases be local adaptation. It was concluded that locations Carlos Botelho and Ilha do Cardoso are the most favorable for seed germination of its same provenance.