Este trabalho apresenta um estudo de inferência e diagnósticos em modelos assimétricos. A análise de influência é baseada na metodologia para modelos com dados incompletos, que é relacionada ao algoritmo EM (Zhu e Lee, 2001). Além dos modelos de regressão Normal Assimétrico (Azzalini, 1999) e t-Normal Assimétrico (Gómez, Venegas e Bolfarine, 2007) existentes, são desenvolvidas duas novas classes de modelos, denominados modelos de misturas de escala normal assimétricos (englobando as distribuições Normal, t-Normal, Slash, Normal-Contaminada e Exponencial-potência Assimétricas) e modelos lineares mistos robustos assimétricos, utilizando distribuições de misturas de escalas normais assimétricas para o efeito aleatório e distribuições de misturas de escalas para o erro aleatório. Para o modelo misto, a matriz de informação de Fisher observada é calculada utilizando a aproximação de Louis (1982) para dados incompletos. Para todos os modelos, algoritmos tipo EM são desenvolvidos de forma a fornecer uma solução numérica para os parâmetros dos modelos de regressão. Para cada modelo de regressão, medidas de bondade de ajuste são realizadas via inspeção visual do gráfico de envelope simulado. Para os modelos de misturas de escalas normais assimétricos, um estudo de robustez do algoritmo EM proposto é desenvolvido, determinando a eficácia dos estimadores apresentados. Aplicações dos modelos estudados são realizadas para os conjuntos de dados do Australian Institute of Sports (AIS), para o conjunto de dados sobre qualidade de vida de pacientes (mulheres) com câncer de mama, em um estudo realizado pelo Centro de Atenção Integral à Saúde da Mulher (CAISM) em conjunto com a Faculdade de Ciências Médicas, da Universidade Estadual de Campinas e para o conjunto de dados de colesterol de Framingham. / This work presents a study of inference and diagnostic in asymmetric models. The influence analysis is based in the methodology for models with incomplete data, that is related to the algorithm EM (Zhu and Lee, 2001). Beyond of the existing asymmetric normal (Azzalini, 1999) and t-Normal asymmetric (Gómez, Venegas and Bolfarine, 2007) regression models, are developed two new classes of models, namely asymmetric normal scale mixture models (embodying the asymmetric Normal, t-Normal, Slash, Contaminated-Normal and Power-Exponential distributions) and asymmetric robust linear mixed models, utilizing asymmetric normal scale mixture distributions for the random effect and normal scale mixture distributions for the random error. For the mixed model, the observed Fisher information matrix is calculated using the Louis\' (1982) approach for incomplete data. For all models, EM algorithms are developed, that provide a numeric solution for the parameters of the regression models. For each regression model, measures of goodness of fit are realized through visual inspection of the graphic of simulated envelope. For the asymmetric normal scale mixture models, a study of robustness of the proposed EM algorithm is developed to determine the efficacy of the presented estimators. Applications of the studied models are made for the data set of the Australian Institute of Sports (AIS), for the data set about quality of life of patients (women) with breast cancer, in a study made by Centro de Atenção Integral à Saúde da Mulher (CAISM) in conjoint with the Medical Sciences Faculty, of the Campinas State\'s University and for the data set of Framingham\'s cholesterol study.

Experimentos conduzidos no delineamento látice ou reticulado são bastante comuns no melhoramento genético vegetal em que diversos materiais genéticos são comparados, principalmente nas etapas iniciais do programa, visando explorar com maior intensidade a variabilidade genética disponível. Em situações de restrições espaciais e financeiras estes delineamentos se destacam por permitir a comparação de todas as progênies em teste estando ou não instaladas no mesmo bloco. O objetivo do trabalho foi a avaliação de testes de progênies de milho (Zea mays L.), em diferentes ambientes para o caráter produção de grãos em t.ha-1. Duzentas e cinquenta e seis progênies foram instaladas em 4 estações experimentais do município de Piracicaba em diferentes anos agrícolas. Os dados de produção de grãos obtidos pelos diferentes ambientes foram analisados de forma individual e conjunta, a fim de verificar presença da interação genótipo × ambiente. O delineamento usado foi, portanto, o látice quadrado 16 × 16, com duas repetições em cada local. Duas abordagens experimentais foram confrontadas, considerando a estrutura de blocos incompletos parcialmente balanceados do látice e a outra em que cada repetição do látice foi analisada como se fosse um bloco completo. Uma maneira de se analisar estruturas experimentais como esta é utilizando modelos mistos, por meio da inclusão de fatores de efeito aleatório e, fazendo o uso da máxima verossimilhança restrita (REML) para estimar os componentes de variância associados a tais fatores com um menor viés. Além dos componentes de variância, os EBLUPs (melhores preditores lineares não viesados empíricos) também foram calculados e a partir deles foi verificada a correlação entre os diferentes ambientes, e a porcentagem de progênies selecionadas comparando-se os resultados obtidos pelas duas abordagens do conjunto de dados. Análises estatísticas foram implementadas utilizando o software gratuito R, com o pacote estatístico lme4. / Experiments conducted in the lattice design are quite common in plant breeding in which several genetic materials are compared, especially in the early stages of the program, aiming to explore more intensively the genetic variability available. In situations of space and financial constraints these designs stand out for allowing the comparison of all progenies being tested whether or not installed in the same block. The aim of the study was the evaluation of maize (Zea mays L.) progeny tests in different environments for grain yield in t.ha-1. Two hundred and fifty six progenies were tested in four experimental stations in the city of Piracicaba, in different agricultural years. Grain production data obtained by different environments were analyzed individually and jointly in order to verify the presence of genotype × environment interaction. Therefore, the square lattice design with dimension 16 × 16 was used with two replications in each location. Two experimental approaches were compared, considering the partially balanced incomplete block structure of the lattice and the other in each repetition of the lattice was analyzed as if it were a complete block. One way to analyze experimental structures like this is with the use of mixed models, by adding random effect factors, and by making use of the restricted maximum likelihood (REML) for estimating the variance components associated with such factors with less bias. Besides the variance components, EBLUPs (empirical best linear predictor unbiased) were also calculated and from them was checked the correlation between the different environments, and the percentage of selected progenies comparing the results obtained by the two assembly approaches data. Statistical analyzes were implemented for the open-souce software R, using the statistical package lme4.

This thesis develops a general strategy for factorial linear model analysis for experimental and observational studies. It satisfactorily deals with a number of issues that have previously caused problems in such analyses. The strategy developed here is an iterative, four-stage, model comparison procedure as described in Brien (1989); it is a generalization of the approach of Nelder (1965a,b). The approach is applicable to studies characterized as being structure-balanced, multitiered and based on Tjur structures unless the structure involves variation factors when it must be a regular Tjur structure. It covers a wide range of experiments including multiple-error, change-over, two-phase, superimposed and unbalanced experiments. Examples illustrating this are presented. Inference from the approach is based on linear expectation and variation models and employs an analysis of variance. The sources included in the analysis of variance table is based on the division of the factors, on the basis of the randomization employed in the study, into sets called tiers. The factors are also subdivided into expectation factors and variation factors. From this subdivision models appropriate to the study can be formulated and the expected mean squares based on these models obtained. The terms in the expectation model may be nonorthogonal and the terms in the variation model may exhibit a certain kind of nonorthogonal variation structure. Rules are derived for obtaining the sums of squares, degrees of freedom and expected mean squares for the class of studies covered. The models used in the approach make it clear that the expected mean squares depend on the subdivision into expectation and variation factors. The approach clarifes the appropriate mean square comparisons for model selection. The analysis of variance table produced with the approach has the advantage that it will reflect all the relevant physical features of the study. A consequence of this is that studies, in which the randomization is such that their confounding patterns differ, will have different analysis of variance tables. / Thesis (Ph.D.)--Department of Plant Science, 1992.

One basic problem in statistical sciences is to understand the relationships among multivariate outcomes. Although it remains an important tool and is widely applicable, the regression analysis is limited by the basic setup that requires to identify one dimension of the outcomes as the primary measure of interest (the "dependent" variable) and other dimensions as supporting this variable (the "explanatory" variables). There are situations where this relationship is not of primary interest. For example, in actuarial sciences, one might be interested to see the dependence between annual claim numbers of a policyholder and its impact on the premium or the dependence between the claim amounts and the expenses related to them. In such cases the normality hypothesis fails, thus Pearson's correlation or concepts based on linearity are no longer the best ones to be used. Therefore, in order to quantify the dependence between non-normal outcomes one needs different statistical tools, such as, for example, the dependence concepts and the copulas. This thesis is devoted to modelling dependence with applications in actuarial sciences and is divided in two parts: the first one concerns dependence in frequency credibility models and the second one dependence between continuous outcomes. In each part of the thesis we resort to different tools, the stochastic orderings (which arise from the dependence concepts), and copulas, respectively. During the last decade of the 20th century, the world of insurance was confronted with important developments of the a posteriori tarification, especially in the field of credibility. This was dued to the easing of insurance markets in the European Union, which gave rise to an advanced segmentation. The first important contribution is due to Dionne & Vanasse (1989), who proposed a credibility model which integrates a priori and a posteriori information on an individual basis. These authors introduced a regression component in the Poisson counting model in order to use all available information in the estimation of accident frequency. The unexplained heterogeneity was then modeled by the introduction of a latent variable representing the influence of hidden policy characteristics. The vast majority of the papers appeared in the actuarial literature considered time-independent (or static) heterogeneous models. Noticeable exceptions include the pioneering papers by Gerber & Jones (1975), Sundt (1988) and Pinquet, Guillén & Bolancé (2001, 2003). The allowance for an unknown underlying random parameter that develops over time is justified since unobservable factors influencing the driving abilities are not constant. One might consider either shocks (induced by events like divorces or nervous breakdown, for instance) or continuous modifications (e.g. due to learning effect). In the first part we study the recently introduced models in the frequency credibility theory, which can be seen as models of time series for count data, adapted to actuarial problems. More precisely we will examine the kind of dependence induced among annual claim numbers by the introduction of random effects taking unexplained heterogeneity, when these random effects are static and time-dependent. We will also make precise the effect of reporting claims on the a posteriori distribution of the random effect. This will be done by establishing some stochastic monotonicity property of the a posteriori distribution with respect to the claims history. We end this part by considering different models for the random effects and computing the a posteriori corrections of the premiums on basis of a real data set from a Spanish insurance company. Whereas dependence concepts are very useful to describe the relationship between multivariate outcomes, in practice (think for instance to the computation of reinsurance premiums) one need some statistical tool easy to implement, which incorporates the structure of the data. Such tool is the copula, which allows the construction of multivariate distributions for given marginals. Because copulas characterize the dependence structure of random vectors once the effect of the marginals has been factored out, identifying and fitting a copula to data is not an easy task. In practice, it is often preferable to restrict the search of an appropriate copula to some reasonable family, like the archimedean one. Then, it is extremely useful to have simple graphical procedures to select the best fitting model among some competing alternatives for the data at hand. In the second part of the thesis we propose a new nonparametric estimator for the generator, that takes into account the particularity of the data, namely censoring and truncation. This nonparametric estimation then serves as a benchmark to select an appropriate parametric archimedean copula. This selection procedure will be illustrated on a real data set.

Nearly 80% of children treated for cancer are expected to survive, but not without cost. Survivors face unprecedented challenges associated with long-term consequences of treatment, also called late effects. Approximately half of children treated for cancer are at risk for experiencing cognitive late effects, which typically emerge several years post diagnosis. The nature and extent of cognitive late effects appear to be developmental and related to patient, disease, and treatment variables. However, the relationships between these variables is not well understood because there have been few prospective and longitudinal studies that report on the contributions of these variables over time. This dissertation examined the effects of patient, disease, and treatment variables, as well as their interactions over time on neurocognitive functioning in childhood cancer survivors. It comprises part of a large prospective, randomized clinical trial designed to examine changes in cognitive function over three years as a function of different levels of monitoring of school-based intervention based on individual educational plans (IEPs). This dissertation uniquely contributed a new measure (the Treatment Intensity Rating Scale) that was used to systematically classify treatment severity across different types of cancer and cancer treatments. Participants included 61 children ages 7 to 12 years at enrollment who were two to five years from completion of treatment for a brain tumor, leukemia, or lymphoma. Participants received yearly neuropsychological evaluations for a follow-up period of 3 years. Results of these evaluations were used to develop IEPs. Participants were randomized to have their IEPs monitored on a quarterly or annual basis for the duration of the study. Contrary to the progressive decline in neurocognitive functioning that is typically anticipated in pediatric cancer survivors, analyses revealed relative stability of performance on neurocognitive measures over time. Higher neurocognitive performance was noted in children whose IEPs were monitored more frequently versus less frequently. Results also supported gender-specific risk for late effects, with lower performance on select neurocognitive measures in females compared to males. Results of this study provide encouraging evidence of the positive effects of school-based interventions and their close monitoring. This has important implications for quality of life as these children survive well beyond childhood into adulthood.

In an experiment to understand colon carcinogenesis, all animals were exposed to a carcinogen while half the animals were also exposed to radiation. Spatially, we measured the existence of aberrant crypt foci (ACF), namely morphologically changed colonic crypts that are known to be precursors of colon cancer development. The biological question of interest is whether the locations of these ACFs are spatially correlated: if so, this indicates that damage to the colon due to carcinogens and radiation is localized. Statistically, the data take the form of binary outcomes (corresponding to the existence of an ACF) on a regular grid. We develop score??type methods based upon the Matern and conditionally autoregression (CAR) correlation models to test for the spatial correlation in such data, while allowing for nonstationarity. Because of a technical peculiarity of the score??type test, we also develop robust versions of the method. The methods are compared to a generalization of Moran??s test for continuous outcomes, and are shown via simulation to have the potential for increased power. When applied to our data, the methods indicate the existence of spatial correlation, and hence indicate localization of damage. Assuming that there are correlations in the locations of the ACF, the questions are how great are these correlations, and whether the correlation structures di?er when an animal is exposed to radiation. To understand the extent of the correlation, we cast the problem as a spatial binary regression, where binary responses arise from an underlying Gaussian latent process. We model these marginal probabilities of ACF semiparametrically, using ?xed-knot penalized regression splines and single-index models. We ?t the models using pairwise pseudolikelihood methods. Assuming that the underlying latent process is strongly mixing, known to be the case for many Gaussian processes, we prove asymptotic normality of the methods. The penalized regression splines have penalty parameters that must converge to zero asymptotically: we derive rates for these parameters that do and do not lead to an asymptotic bias, and we derive the optimal rate of convergence for them. Finally, we apply the methods to the data from our experiment.

Background: Childhood excess weight and family food insecurity are food-system related public health problems that exist in Canada. Since both relate to issues of food accessibility and availability, which have elements of “place”, they may share common risk factors in the local environment that are amenable to intervention. In this area of research, the literature derives mostly from a US context, and there is a dearth of high quality evidence, specifically from longitudinal studies. Objectives: The main objectives of this thesis were to examine the adjusted associations between the place factors: material deprivation, social deprivation, social cohesion, disorder, and living location, with change in child BMI Z-score and with change in family food insecurity status in a Canadian cohort of children. Methods: The Québec Longitudinal Study of Child Development was used to meet the main objectives of this thesis. Response data from six collection cycles (4 – 10 years of age) were used in three main analyses. The first analysis examined change in child BMI Z-score as a function of the place factors using mixed models regression. The second analysis examined change in child BMI Z-score as a function of place factors using group-based trajectory modeling. The third and final analysis examined change in family food insecurity status as a function of the place factors using generalized estimating equations. Results: Social deprivation, social cohesion and disorder were strongly and positively associated with family food insecurity, increasing the odds by 45-76%. These place factors, on the other hand, were not consistently associated with child weight status. Material deprivation was not important for either outcome, except for a slight positive association in the mixed models analysis of child weight status. Living location was not important in explaining family food insecurity. On the other hand, it was associated with child weight status in both analyses, but the nature of the relationship is still unclear. Conclusions: Results do not suggest that addressing similar place factors may alleviate both child excess weight and family food insecurity. More high quality longitudinal and experimental studies are needed to clarify relationships between the local environment and child weight status and family food insecurity.

In an experiment to understand colon carcinogenesis, all animals were exposed to a carcinogen while half the animals were also exposed to radiation. Spatially, we measured the existence of aberrant crypt foci (ACF), namely morphologically changed colonic crypts that are known to be precursors of colon cancer development. The biological question of interest is whether the locations of these ACFs are spatially correlated: if so, this indicates that damage to the colon due to carcinogens and radiation is localized. Statistically, the data take the form of binary outcomes (corresponding to the existence of an ACF) on a regular grid. We develop score??type methods based upon the Matern and conditionally autoregression (CAR) correlation models to test for the spatial correlation in such data, while allowing for nonstationarity. Because of a technical peculiarity of the score??type test, we also develop robust versions of the method. The methods are compared to a generalization of Moran??s test for continuous outcomes, and are shown via simulation to have the potential for increased power. When applied to our data, the methods indicate the existence of spatial correlation, and hence indicate localization of damage. Assuming that there are correlations in the locations of the ACF, the questions are how great are these correlations, and whether the correlation structures di?er when an animal is exposed to radiation. To understand the extent of the correlation, we cast the problem as a spatial binary regression, where binary responses arise from an underlying Gaussian latent process. We model these marginal probabilities of ACF semiparametrically, using ?xed-knot penalized regression splines and single-index models. We ?t the models using pairwise pseudolikelihood methods. Assuming that the underlying latent process is strongly mixing, known to be the case for many Gaussian processes, we prove asymptotic normality of the methods. The penalized regression splines have penalty parameters that must converge to zero asymptotically: we derive rates for these parameters that do and do not lead to an asymptotic bias, and we derive the optimal rate of convergence for them. Finally, we apply the methods to the data from our experiment.

The class of models which is studied in this paper, multi-unit longitudinal models, combines both the cross-sectional and the longitudinal aspects of observations. Many empirical investigations involve the analysis of data structures that are both cross-sectional (observations are taken on several units at a specific time period or at a specific location) and longitudinal (observations on the same unit are taken over time or space). Multi-unit longitudinal data structures arise in economics and business where panels of subjects are studied over time, biostatistics where groups of patients on different treatments are observed over time, and in situations where data are taken over time and space. Modelling issues in multi-unit longitudinal models with random coefficients and patterned correlation structure are illustrated in the context of two data sets. The first data set deals with short time series data on annual death rates and alcohol consumption for twenty-five European countries. The second data set deals with glaceologic time series data on snow temperature at 14 different locations within a small glacier in the Austrian Alps. A practical model building approach, consisting of model specification, estimation, and diagnostic checking, is outlined. (author's abstract) / Series: Forschungsberichte / Institut für Statistik

The overall aim of this thesis was to explore therapeutic action in psychoanalytic psychotherapy from different perspectives (patient, therapist, observer), using different methodological approaches (qualitative and quantitative). Study I explores patients’ views of therapeutic action with grounded theory methodology. The results indicated that talking openly in a safe therapeutic relationship led to new relational experiences and expanding self-awareness. Hindering factors included difficulties “opening up” and experiencing something missing in treatment. Study II investigates experienced therapists’ views of therapeutic action. The development of a close and trusting relationship was perceived as the core curative factor. Patients’ fear of closeness hindered treatment from the therapists’ perspective. Study III involves the development and psychometric examination of a new rating scale for patient-therapist attachment (Patient Attachment to Therapist Rating Scale; PAT-RS). Inter-rater reliability was good for three of the subscales (Security, Deactivation, Disorganization), but poor for one (Hyperactivation). Patterns of correlations with other measures suggest construct validity for the reliable subscales. Study IV examines the relationships between secure attachment to therapist, alliance, and outcome. Linear mixed-effects models, controlling for therapist effects, treatment length and patient-rated alliance, indicated that secure attachment to therapist relates to outcome. Further, the unique variance associated with secure attachment to therapist predicted continued gains in functioning during follow-up. The results of this thesis suggest that the development of a secure attachment to the therapist is a central mechanism of therapeutic change. The results are discussed in relation to established notions of therapeutic action in psychoanalytic psychotherapy. Two tentative process models that may be useful for clinical practice and future research are proposed. / <p>At the time of the doctoral defense, the following paper was unpublished and had a status as follows: Paper 4: Epub ahead of print.</p>