Made available in DSpace on 2015-03-26T13:32:15Z (GMT). No. of bitstreams: 1 texto completo.pdf: 1213757 bytes, checksum: a4899ab14bd6c737501e8ef972e42d9e (MD5) Previous issue date: 2012-02-01 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / In logistic mixed models with random effect on intercept allows capturing the effects of sources of variation from the particular characteristics of a group (heterogeneity), deflating the pure error and causing a fluctuation in the model intercept. This inclusion brings complexity in estimation methods and also changes the interpretation of the parameters that, originally given by the odds ratio, is then seen from the median odds ratio. The estimation parameters of a mixed model can be made by many different methods with varying performance, as the Laplace s approximation method, maximum likelihood (ML) and restricted maximum likelihood (REML). The objective of this work was to verify in logistic mixed models with random effects on intercept the consequences in interpretation of parameters, in quality of experiment and in classification of treatment via the median odds ratio, and verify the performance of the estimation methods above cited. The analyzes were performed under simulation and after in set of real data from seeds germination experiment of physic nut (Jatropha curcas L.). Considering the logistic mixed model with random effects on intercept, it was verified that the REML estimation method performed better and that the variance of the random effect affects the performance of any of these methods being evaluated inversely proportional. We suggest further studies to determine more properly the influence of the inflexion points and the effective median level in performance methods. In the experiment to evaluate the seeds germination of physic nut involving roll paper, on paper, on sand and between sand substrates, the inclusion of random effects in logistic model showed considerable heterogeneity in seeds germination in different units of the same substrate. The median odds ratio showed the superiority of the substrate between sand over on paper in seeds germination of physic nut, result similar to that obtained by the Tukey s test. / Em modelos de regressão logística a inclusão do efeito aleatório no intercepto permite capturar os efeitos de fontes de variação provenientes das características particulares de um grupo (heterogeneidade), desinflacionando o erro puro e provocando uma flutuação no intercepto do modelo. Esta inclusão traz complexidade nos métodos de estimação e também muda a interpretação dos parâmetros que, dada originalmente pela razão de chances, passa a ser vista sob o enfoque da razão de chances mediana. A estimação dos parâmetros de um modelo misto pode ser feita por muitos métodos diferentes com desempenho variado, como o método da aproximação de Laplace, da máxima verossimilhança (ML) e da máxima verossimilhança restrita (REML). Assim, o objetivo deste trabalho foi verificar em modelos de regressão logística com efeito aleatório no intercepto as consequências na interpretação dos parâmetros, na qualidade de um experimento e na classificação de tratamentos via razão de chances mediana, e verificar o desempenho dos métodos de estimação acima citados. As análises foram feitas sob simulação e posteriormente num conjunto de dados reais de um experimento com germinação de sementes de pinhão-manso (Jatropha curcas L.). Considerando o modelo de regressão logística com efeito aleatório no intercepto, verificou-se que o método de estimação REML apresentou melhor desempenho e que a variância do efeito aleatório afeta o desempenho de qualquer um dos métodos avaliados sendo estes inversamente proporcionais. Sugerem-se novos estudos para determinar com mais propriedade a influência dos pontos de estabilização e do nível mediano de efetividade na eficiência dos métodos. No experimento de avaliação de germinação de sementes de pinhão-manso envolvendo os substratos rolo de papel, sobre papel, sobre areia e entre areia, a inclusão do efeito aleatório no modelo logístico apontou considerável heterogeneidade na germinação de sementes em unidades diferentes de um mesmo substrato. A razão de chances mediana apontou a superioridade do substrato entre areia em relação a sobre papel na germinação de sementes de pinhão-manso, resultado semelhante ao obtido pelo teste de Tukey.

Les applications récentes telles que les bases de données forestières impliquent des observations de données spatiales associées à l'observation de nombreuses covariables spatiales. Nous considérons dans cette thèse le problème de l'estimation d'une forme paramétrique de la fonction d'intensité dans un tel contexte. Cette thèse développe les procédures de sélection des variables et donne des garanties quant à leur validité. En particulier, nous proposons deux approches différentes pour la sélection de variables : les méthodes de type lasso et les procédures de type Sélecteur de Dantzig. Pour les méthodes envisageant les techniques de type lasso, nous dérivons les propriétés asymptotiques des estimations obtenues par les fontions d'estimation dérivées par les vraisemblances de la Poisson et de la régression logistique pénalisées par une grande classe de pénalités. Nous prouvons que les estimations obtenues par de ces procédures satisfont la consistance, sparsité et la normalité asymptotique. Pour la partie sélecteur de Dantzig, nous développons une version modifiée du sélecteur de Dantzig, que nous appelons le sélecteur Dantzig linéaire adaptatif (ALDS), pour obtenir les estimations d'intensité. Plus précisément, les estimations ALDS sont définies comme la solution à un problème d'optimisation qui minimise la somme des coefficients des estimations soumises à une approximation linéaire du vecteur score comme une contrainte. Nous constatons que les estimations obtenues par de ces méthodes ont des propriétés asymptotiques semblables à celles proposées précédemment à l'aide de méthode régularisation du lasso adaptatif. Nous étudions les aspects computationnels des méthodes développées en utilisant les procédures de type lasso et de type Sélector Dantzig. Nous établissons des liens entre l'estimation de l'intensité des processus ponctuels spatiaux et les modèles linéaires généralisés (GLM), donc nous n'avons qu'à traiter les procédures de la sélection des variables pour les GLM. Ainsi, des procédures de calcul plus faciles sont implémentées et un algorithme informatique rapide est proposé. Des études de simulation sont menées pour évaluer les performances des échantillons finis des estimations de chacune des deux approches proposées. Enfin, nos méthodes sont appliquées pour modéliser les emplacements spatiaux, une espèce d'arbre dans la forêt observée avec un grand nombre de facteurs environnementaux. / Recent applications such as forestry datasets involve the observations of spatial point pattern data combined with the observation of many spatial covariates. We consider in this thesis the problem of estimating a parametric form of the intensity function in such a context. This thesis develops feature selection procedures and gives some guarantees on their validity. In particular, we propose two different feature selection approaches: the lasso-type methods and the Dantzig selector-type procedures. For the methods considering lasso-type techniques, we derive asymptotic properties of the estimates obtained from estimating functions derived from Poisson and logistic regression likelihoods penalized by a large class of penalties. We prove that the estimates obtained from such procedures satisfy consistency, sparsity, and asymptotic normality. For the Dantzig selector part, we develop a modified version of the Dantzig selector, which we call the adaptive linearized Dantzig selector (ALDS), to obtain the intensity estimates. More precisely, the ALDS estimates are defined as the solution to an optimization problem which minimizes the sum of coefficients of the estimates subject to linear approximation of the score vector as a constraint. We find that the estimates obtained from such methods have asymptotic properties similar to the ones proposed previously using an adaptive lasso regularization term. We investigate the computational aspects of the methods developped using either lasso-type procedures or the Dantzig selector-type approaches. We make links between spatial point processes intensity estimation and generalized linear models (GLMs), so we only have to deal with feature selection procedures for GLMs. Thus, easier computational procedures are implemented and computationally fast algorithm are proposed. Simulation experiments are conducted to highlight the finite sample performances of the estimates from each of two proposed approaches. Finally, our methods are applied to model the spatial locations a species of tree in the forest observed with a large number of environmental factors.

O problema de Inferência sobre uma proporção, amplamente divulgado na literatura estatística, ocupa papel central no desenvolvimento das várias teorias de Inferência Estatística e, invariavelmente, é objeto de investigação e discussão em estudos comparativos entre as diferentes escolas de Inferência. Ademais, a estimação de proporções, bem como teste de hipóteses para proporções, é de grande importância para as diversas áreas do conhecimento, constituindo um método quantitativo simples e universal. Nesse trabalho, é feito um estudo comparativo entre as abordagens clássica e bayesiana do problema de testar as hipóteses de ocorrência ou não de 2º turno em um cenário típico de eleição majoritária (maioria absoluta) em dois turnos no Brasil. / The problem of inference about a proportion, widely explored in the statistical literature, plays a key role in the development of several theories of statistical inference and, invariably, is the object of investigation and discussion in comparative studies among different schools of inference. In addition, the estimation of proportions, as well as test of hypothesis for proportions, is very important in many areas of knowledge as it constitutes a simple and universal quantitative method. In this work a comparative study between the Classical and Bayesian approaches to the problem of testing the hypothesis of occurrence of second round (or not) in a typical scenario of a majoritarian election (absolute majority) in two rounds in Brazil is developed.

Mathematical and computational epidemiological models are important tools in efforts to combat the spread of infectious diseases. The models can be used to predict further progression of an epidemic and for assessing potential countermeasures to control disease spread. In the proposal of models (when data is available), one needs parameter estimation methods. In this thesis, likelihood-less Bayesian inference methods are concerned. The data and the model originate from the spread of a verotoxigenic Escherichia coli in the Swedish cattle population. In using the SISE3 model, which is an extension of the susceptible-infected-susceptible model with added environmental pressure and three age categories, two different methods were employed to give an estimated posterior: Approximate Bayesian Computations and Synthetic Likelihood Markov chain Monte Carlo. The mean values of the resulting posteriors were close to the previously performed point estimates, which gives the conclusion that Bayesian inference on a nation scaled SIS-like network is conceivable.

Improving the estimation efficiency has always been one of the important aspects in statistical modelling. Our goal is to develop new statistical methodologies yielding more efficient estimators in the analysis of longitudinal data. In this thesis, we consider two different approaches, empirical likelihood and jointly modelling the mean and variance, to improve the estimation efficiency. In part I of this thesis, empirical likelihood-based inference for longitudinal data within the framework of generalized linear model is investigated. The proposed procedure takes into account the within-subject correlation without involving direct estimation of nuisance parameters in the correlation matrix and retains optimality even if the working correlation structure is misspecified. The proposed approach yields more efficient estimators than conventional generalized estimating equations and achieves the same asymptotic variance as quadratic inference functions based methods. The second part of this thesis focus on the joint mean-variance models. We proposed a data-driven approach to modelling the mean and variance simultaneously, yielding more efficient estimates of the mean regression parameters than the conventional generalized estimating equations approach even if the within-subject correlation structure is misspecified in our joint mean-variance models. The joint mean-variances in parametric form as well as semi-parametric form has been investigated. Extensive simulation studies are conducted to assess the performance of our proposed approaches. Three longitudinal data sets, Ohio Children’s wheeze status data (Ware et al., 1984), Cattle data (Kenward, 1987) and CD4+ data (Kaslowet al., 1987), are used to demonstrate our models and approaches.

This thesis concentrates on regression models with a categorical response. It focuses on the model of logistic regression with binary response and its generalization in which two models are distinguished: multinomial regression with nominal response and multinomial regression with ordinal response. For all three models separately, the Wald test and the likelihood ratio test are derived. These theoretical derivations are then used to calculate the test statistics for specific examples in statistical software R. The theory described in the thesis is illustrated by examples with small and large number of explanatory variables.

This thesis deals with training dataset and validation dataset for Earth observation classification accuracy improvement. Experiments with training data and validation data for two classification algorithms (Maximum Likelihood - MLC and Support Vector Machine - SVM) are carried out from the forest-meadow landscape located in the foothill of the Giant Mountains (Podkrkonoší). The thesis is base on the assumption that 1/3 of training data and 2/3 of validation data is an ideal ratio to achieve maximal classification accuracy (Foody, 2009). Another hypothesis was that in a case of SVM classification, a lower number of training point is required to achieve the same or similar accuracy of classification, as in the case of the MLC algorithm (Foody, 2004). The main goal of the thesis was to test the influence of proportion / amount of training and validation data on the classification accuracy of Sentinel - 2A multispectral data using the MLC algorithm. The highest overal accuracy using the MLC classification algorithm was achieved for 375 training and 625 validation points. The overal accuracy for this ratio was 72,88 %. The theory of Foody (2009) that 1/3 of training data and 2/3 of validation data is an ideal ratio to achieve the highest classification accuracy, was confirmed by the overal accuracy and...

In this thesis we are interested in generalized estimating equations (GEE). First, we introduce the term of generalized linear model, on which generalized estimating equations are based. Next we present the methos of pseudo maximum likelyhood and quasi-pseudo maximum likelyhood, from which we move on to the methods of generalized estimating equations. Finally, we perform simulation studies, which demonstrates the theoretical results presented in the thesis. 1

Covid-19-pandemin och åtföljande restriktioner gjorde det svårt för konsumenter att integrera både online och offline kanaler. Syftet med studien är att få en förståelse över hur pandemin har förändrat konsumenters kanalstrategier i detaljhandeln, och vilka kanaler konsumenter börjat föredra att använda sig av vid shopping. För att studera detta har vi tillämpats oss av Elaboration likelihood model för att med hjälp av insamlad empiri förstå hur konsumenters informationsbearbetning i online och offline kanaler formar deras strategier att kombinera kanaler. Datamaterialet består av en kvalitativ metod i form av enskilda intervjuer och fokusgrupper, med 26 respondenter sammanlagt. I samband med pandemin visar resultatet på att respondenterna övergick från att utföra spontana till mer planerade inköp. Den största anledning till denna förändring är att shopping i fysiska butiker inte var lika roligt på grund av de nya restriktionerna som bland annat gjorde så att provrummen stängdes ned. Resultatet visar även på att informationsbearbetningen i online och offline kanaler är bidragande i skapandet av respondenternas kanalstrategier. Respondenterna hade olika sätt att behandla informationen som presenterats för dem, och utformade därifrån kanalstrategier. Sammanfattningsvis kan vi konstatera att beroende på hur respondenten behandlar informationen som presenterats, leder detta i sin tur till skapandet av kanalstrategier. Detta förklarar varför respondenterna som behandlade informationen via ELM’s centrala eller perifera kanal hade olika kanalstrategier. / The Covid-19 pandemic and associated restrictions made it difficult for consumers to integrate both online and offline channels. The purpose of the study is to gain an understanding of how the pandemic has changed consumers' channel strategies in retail, and which channels consumers have begun to prefer to use when shopping. To study this, we have applied the Elaboration likelihood model to use collected empirical data to understand how consumers' information processing in online and offline channels shapes their strategies for combining channels. The data material consists of a qualitative method in the form of individual interviews and focus groups, with a total of 26 respondents. In connection with the pandemic, the results show that the respondents switched from making spontaneous to more planned purchases. The main reason for this change is that shopping in physical stores was not as fun due to the new restrictions that, among other things, caused the rehearsal rooms to be closed. The results also show that information processing in online and offline channels contributes to the creation of respondents' channel strategies. The respondents had different ways of processing the information presented to them, and from there devised channel strategies. In summary, we can state that depending on how the respondent processes the information presented, this in turn leads to the creation of channel strategies. This explains why the respondents who processed the information via ELM's central or peripheral channel had different channel strategies.

No description available.