Em ensaios clínicos é muito comum a ocorrência de dados longitudinais discretos. Para sua análise é necessário levar em consideração que dados observados na mesma unidade experimental ao longo do tempo possam ser correlacionados. Além dessa correlação inerente aos dados é comum ocorrer o fenômeno de superdispersão (ou sobredispersão), em que, existe uma variabilidade nos dados além daquela captada pelo modelo. Um caso que pode acarretar a superdispersão é o excesso de zeros, podendo também a superdispersão ocorrer em valores não nulos, ou ainda, em ambos os casos. Molenberghs, Verbeke e Demétrio (2007) propuseram uma classe de modelos para acomodar simultaneamente a superdispersão e a correlação em dados de contagens: modelo Poisson, modelo Poisson-gama, modelo Poisson-normal e modelo Poisson-normal-gama (ou modelo combinado). Rizzato (2011) apresentou a abordagem bayesiana para o ajuste desses modelos por meio do Método de Monte Carlo com Cadeias de Markov (MCMC). Este trabalho, para modelar a incerteza relativa aos parâmetros desses modelos, considerou a abordagem bayesiana por meio de um método determinístico para a solução de integrais, INLA (do inglês, Integrated Nested Laplace Approximations). Além dessa classe de modelos, como objetivo, foram propostos outros quatros modelos que também consideram a correlação entre medidas longitudinais e a ocorrência de superdispersão, além da ocorrência de zeros estruturais e não estruturais (amostrais): modelo Poisson inacionado de zeros (ZIP), modelo binomial negativo inacionado de zeros (ZINB), modelo Poisson inacionado de zeros - normal (ZIP-normal) e modelo binomial negativo inacionado de zeros - normal (ZINB-normal). Para ilustrar a metodologia desenvolvida, um conjunto de dados reais referentes à contagens de ataques epilépticos sofridos por pacientes portadores de epilepsia submetidos a dois tratamentos (um placebo e uma nova droga) ao longo de 27 semanas foi considerado. A seleção de modelos foi realizada utilizando-se medidas preditivas baseadas em validação cruzada. Sob essas medidas, o modelo selecionado foi o modelo ZIP-normal, sob o modelo corrente na literatura, modelo combinado. As rotinas computacionais foram implementadas no programa R e são parte deste trabalho. / Discrete and longitudinal structures naturally arise in clinical trial data. Such data are usually correlated, particularly when the observations are made within the same experimental unit over time and, thus, statistical analyses must take this situation into account. Besides this typical correlation, overdispersion is another common phenomenon in discrete data, defined as a greater observed variability than that nominated by the statistical model. The causes of overdispersion are usually related to an excess of observed zeros (zero-ination), or an excess of observed positive specific values or even both. Molenberghs, Verbeke e Demétrio (2007) have developed a class of models that encompasses both overdispersion and correlation in count data: Poisson, Poisson-gama, Poisson-normal, Poissonnormal- gama (combined model) models. A Bayesian approach was presented by Rizzato (2011) to fit these models using the Markov Chain Monte Carlo method (MCMC). In this work, a Bayesian framework was adopted as well and, in order to consider the uncertainty related to the model parameters, the Integrated Nested Laplace Approximations (INLA) method was used. Along with the models considered in Rizzato (2011), another four new models were proposed including longitudinal correlation, overdispersion and zero-ination by structural and random zeros, namely: zero-inated Poisson (ZIP), zero-inated negative binomial (ZINB), zero-inated Poisson-normal (ZIP-normal) and the zero-inated negative binomial-normal (ZINB-normal) models. In order to illustrate the developed methodology, the models were fit to a real dataset, in which the response variable was taken to be the number of epileptic events per week in each individual. These individuals were split into two groups, one taking placebo and the other taking an experimental drug, and they observed up to 27 weeks. The model selection criteria were given by different predictive measures based on cross validation. In this setting, the ZIP-normal model was selected instead the usual model in the literature (combined model). The computational routines were implemented in R language and constitute a part of this work.

In this thesis I analyse sub-national differences in the employment trajectories of mothers of young children in Germany (Bundeslaender) and the UK (Government Office Regions and Metropolitan counties). The thesis combines longitudinal and spatial approaches to paid work, and focuses on mothers of children under 6 - arguably the group at the core of the social (re)production of gender differences in employment. One of its aims is to nuance the existing literature explaining the differences in women's involvement in paid work in terms of national welfare and/or breadwinner regimes - by looking at the nature and extent of regional variations in the patterns of involvement that make these countries typical of such regimes. Its specific goals consist in testing the Latent Growth Curve (LCM) framework as a method for modelling variations in participation in paid work over time, then in exploring three possible explanations for the regional differences observed. The respective role of regional differences in the family formation and social position of the maternal labour force, of the availability of suitable jobs in particular segregated jobs, and finally of economic histories in relation to women's orientations to work is assessed. The results confirmed that LCM represents an innovative tool to understand variations of involvement in paid work over time, and revealed significant regional differences, beyond the 'North South' and 'East-West' divides documented respectively in the UK and Germany. In both countries, results pointed at a combined effect of the three explanatory factors analysed. Whilst composition and labour demands effects went some way towards explaining some of the variations observed, at the same time additional regional variations were discovered once composition factors were taken into account. Finally the pattern of association between the remaining unexplained regional variation and aggregate attitudes of women towards paid work suggests an influence of long term trends in participation on present levels of involvement.

Why do students choose to study particular courses and what is the impact of these choices on their later progression? Quite often the reason for the choice appears to be obvious and straightforward, and their after course trajectory is already determined. The education system has, what some may view as an easy to follow progression route when students reach the end of Key Stage 4, i.e. GCSE to A level, and then university for those who meet the criteria. With A levels considered by many to be the 'gold standard', there is probably no expectation by schools, parents and students that they will do anything else. But what about those who may not meet the criteria and A levels may not be the most appropriate progression route for them? This thesis examines the factors that influence the choices made by students who have decided to study a course other than A level. This is done through longitudinal case studies derived from the use of questionnaires, focus groups and individual interviews using BTEC L3 Science as a vehicle. Four educational establishments agreed to participate in the research to varying degrees, with one establishment providing the participants who provided the case studies. Many previous studies that have investigated student choice have often done so from either the perspective of structural factors or individual agency, but not usually both. Hemsley-Brown and Fosketts' 2001 Integrated Model of Educational Choice has been used to provide a theoretical framework as it allows consideration of both structural factors and individual agency. The model was used at two different points in the research, but in a different way at each point. The result was a series of individual stories that gave an insight into the factors that influence student choice and also how the balance of power in the decision making process shifted in favour of the student as they progressed through the course. At the start of the course structural factors such as the systems that exist within education had a significant role in the choice of course for the students, to the point where it was effectively a 'non-choice' for them. By the end of the course individual agency played a significant role and the students were able to adapt and make the systems work for them to enable them to make the best possible choices to meet their own needs.

My PhD work aimed to assess intergenerational transmission and life-course change of attitudes towards authority. Intergenerational transmission is hypothesised as the mechanism through which parents' authoritarian attitudes affect their children's attitudes towards authority in adulthood. In the assessment of this transmission mechanism, this analysis accounts for individual-level theoretically relevant factors such as gender, education, social class, offspring's cognitive ability in childhood, as well as family background, in a longitudinal, single-cohort perspective. The research used the British Cohort Study 1970 (BCS70), which allows for the analysis of change at both the intra- and inter-individual levels. The sweeps analysed are those in years 1975 for the parents, and 1980, 1996, 2000 and 2012 for the cohort members. The analytical chapters of the thesis are made of three papers: The first assessed change (or stability) in attitudes to authority in the BCS70 from 1996 to 2012; the second looked at how parental authoritarian worldviews affect their children's attitudes towards authority when the children are adults; finally, the third paper aimed to evaluate the effect of parental attitudes on cohort members' attitudes towards authority in adulthood, after controlling for the latter's cognitive ability in childhood. I found that attitudes had a reasonably high level of stability across the life course. Despite moderately strong correlations across attitudes within waves, the different attitudes showed different patterns of longitudinal evolution, suggesting different causal influences. The evidence for direct transmission of attitudes from parents to children was surprisingly weak; the social statuses of the parents and cohort members, and especially the members' childhood cognitive ability, were the strongest predictors of authoritarian attitudes in adulthood.

Objectives The development of aggression from childhood to adulthood is well-researched, and extant work has identified a large number of developmental risk factors within the individual, family, and social domains. Among them, poor parenting, including harsh practices like corporal punishment, have repeatedly been found to predict adolescent behavioural problems, that may then negatively affect adult behaviours such as violence and offending. An area of research that is becoming increasingly important is one that seeks to identify the reasons why some people do not become aggressive, even when they have been exposed to well established risk factors. What is it that has protected them from becoming aggressive later in life? The current study examined whether self-control and having a positive teacher-child relationship acted as protective factors between corporal punishment and adolescent aggression. Methods An autoregressive cross-lagged panel model was used to examine self-control and teacher-child relationships as both direct and interactive protective factors between corporal punishment and adolescent aggression. Teacher and self-reported data was used from three waves (waves 4-6) of the Zurich Project on the Social Development of Children and Youths (Z-proso), a prospective longitudinal study of adolescents in Switzerland. Results The results show that both self-control and having a positive teacher-child relationship were direct protective factors against concurrent aggression. However, the interactive protective effect of these factors differed depending on the stage of adolescence and level of exposure to risk. Furthermore, differences were found when considering males and females separately.

This dissertation addresses problems found in observational cohort studies where the repeated outcomes of interest are truncated by both death and by dropout. In particular, we consider methods that make inference for the population of survivors at each time point, otherwise known as 'partly conditional inference'. Partly conditional inference distinguishes between the reasons for missingness; failure to make this distinction will cause inference to be based not only on pre-death outcomes which exist but also on post-death outcomes which fundamentally do not exist. Such inference is called 'immortal cohort inference'. Investigations of health and cognitive outcomes in two studies - the 'Origins of Variance in the Old Old' and the 'Health and Retirement Study' - are conducted. Analysis of these studies is complicated by outcomes of interest being missing because of death and dropout. We show, first, that linear mixed models and joint models (that model both the outcome and survival processes) produce immortal cohort inference. This makes the parameters in the longitudinal (sub-)model difficult to interpret. Second, a thorough comparison of well-known methods used to handle missing outcomes - inverse probability weighting, multiple imputation and linear increments - is made, focusing particularly on the setting where outcomes are missing due to both dropout and death. We show that when the dropout models are correctly specified for inverse probability weighting, and the imputation models are correctly specified for multiple imputation or linear increments, then the assumptions of multiple imputation and linear increments are the same as those of inverse probability weighting only if the time of death is included in the dropout and imputation models. Otherwise they may not be. Simulation studies show that each of these methods gives negligibly biased estimates of the partly conditional mean when its assumptions are met, but potentially biased estimates if its assumptions are not met. In addition, we develop new augmented inverse probability weighted estimating equations for making partly conditional inference, which offer double protection against model misspecification. That is, as long as one of the dropout and imputation models is correctly specified, the partly conditional inference is valid. Third, we describe methods that can be used to make partly conditional inference for non-ignorable missing data. Both monotone and non-monotone missing data are considered. We propose three methods that use a tilt function to relate the distribution of an outcome at visit j among those who were last observed at some time before j to those who were observed at visit j. Sensitivity analyses to departures from ignorable missingness assumptions are conducted on simulations and on real datasets. The three methods are: i) an inverse probability weighted method that up-weights observed subjects to represent subjects who are still alive but are not observed; ii) an imputation method that replaces missing outcomes of subjects who are alive with their conditional mean outcomes given past observed data; and iii) a new augmented inverse probability method that combines the previous two methods and is doubly-robust against model misspecification.

COELHO-BARROS, E. A. Analise estatstica para dados de contagem longitudinais na presenca de covariaveis: Aplicações na area medica. Dissertação (mestrado) - Faculdade de Medicina de Ribeirão Preto - USP, Ribeirão Preto - SP - Brasil, 2009. Dados de contagem ao longo do tempo na presenca de covariaveis são muito comuns em estudos na area da saude coletiva, por exemplo; numero de doenças que uma pessoa, com alguma caracteristica especifica, adquiriu ao longo de um período de tempo; numero de internações hospitalares em um período de tempo, devido a algum tipo de doença; numero de doadores de orgãos em um período de tempo. Nesse trabalho são apresentados diferentes modelos estatsticos de\\fragilidade\" de Poisson para a analise estatística de dados de contagem longitudinais. Teoricamente, a distribuição de Poisson exige que a media seja igual a variância, quando isto não ocorre tem-se a presenca de uma variabilidade extra-Poisson. Os modelos estatsticos propostos nesta dissertação incorporam a variabilidade extra-Poisson e capturam uma possvel correlação entre as contagens para o mesmo indivduo. Para cada modelo foi feito uma analise Bayesiana Hierarquica considerando os metodos MCMC (Markov Chain Monte Carlo). Utilizando bancos de dados reais, cedidos por pesquisadores auxiliados pelo CEMEQ (Centro de Metodos Quantitativos, USP/FMRP), foram discutidos alguns aspectos de discriminação Bayesiana para a escolha do melhor modelo. Um exemplo de banco de dados reais, discutido na Seção 4 dessa dissertação, que se encaixa na area da saude coletiva, e composto de um estudo prospectivo, aberto e randomizado, realizado em pacientes infectados pelo HIV que procuraram atendimento na Unidade Especial de Terapia de Doencas Infecciosas (UETDI) do Hospital das Clnicas da Faculdade de Medicina de Ribeirão Preto da Universidade de São Paulo (HCFMRP-USP). Os esquemas terapêuticos estudados consistiam em zidovudina e lamivudina, associadas ao efavirenz ou lopinavir. Entre setembro de 2004 e maio de 2006 foram avaliados 66 pacientes, sendo 43 deles includos no estudo. Destes, 39 participantes alcançaram a semana 24 de acompanhamento, enquanto 27 atingiram a semana 48. Os grupos de pacientes apresentavam características basais semelhantes, quanto a idade, sexo, mediana de CD4 e carga viral. O interesse desse experimento e estudar a contagem de CD4 considerando os dois esquemas terapêuticos (efavirenz e lopinavir). / COELHO-BARROS, E. A. Analise estatstica para dados de contagem longitudinais na presenca de covariaveis: Aplicac~oes na area medica. Dissertac~ao (mestrado) - Faculdade de Medicina de Ribeir~ao Preto - USP, Ribeir~ao Preto - SP - Brasil, 2009. Longitudinal counting data in the presence of covariates is very common in many applications, especially considering medical data. In this work we present dierent \\frailty\"models to analyze longitudinal Poisson data in the presence of covariates. These models incorporate the extra-Poisson variability and the possible correlation among the repeated counting data for each individual. A hierarchical Bayesian analysis is introduced for each dierent model considering usual MCMC (Markov Chain Monte Carlo) methods. Considering reals biological data set (obtained from CEMEQ, Medical School of Ribeir~ao Preto, University of S~ao Paulo, Brazil), we also discuss some Bayesian discrimination aspects for the choice of the best model. In Section 4 is considering a data set related to an open prospective and randomized study, considering of HIV infected patients, free of treatments, which entered the Infection Diseases Therapy Special Unit (UETDI) of the Clinical Hospital of the Medical School of Ribeir~ao Preto, University of S~ao Paulo (HCFMRP-USP). The therapeutic treatments consisted of the drugs Zidovudine and Lamivudine, associated to Efavirenz and Lopinavir. The data set was related to 66 patients followed from September, 2004 to may, 2006, from which, 43 were included in the study. The patients groups presented similar basal characteristics in terms of sex, age, CD4 counting median and viral load. The main goal of this study was to compare the CD4 cells counting for the two treatments, based on the drugs Efavirenz and Lopinavir, recently adopted as preferencial for the initial treatment of the disease.

This study conceptualises Chinese language-major undergraduates' motivation to learn a third language (L3) from a self perspective. Two overarching aims were adopted to guide the research: how learners' L3 motivation was formulated and reformulated over the course of one year of learning an L3 and whether classroom intervention could help learners to construct their L3 motivation. This research adopted a longitudinal case study design and was situated in a state university in China. Students who had chosen to learn an L3 as their major and English majors who were required to learn an L3 participated in the research. To achieve the two principal research aims, the data collection process was divided into two phases. The goal of the first phase was to explore the development of my participants' L3 motivation without any intervention. Qualitative research methods were employed during this phase and data were gathered from open questionnaires, interviews, class observation and written journals. In the second phase, an intervention was carried out to explore how to construct my participants' ideal L3 selves. A quasi-experimental design was employed and mixed methods were adopted. Analysis was primarily guided by the L2 Motivational Self System and was carried out at both at class level and individual level. At a class level, findings suggest that both L3 majors' and English majors' L3 motivation was mainly constituted on the basis of their ideal L3 selves, ought-to L3 selves and L3 learning experiences, which were constantly constructed and reconstructed over the course of learning. Notably, learners' motivational trajectories did not display a homogenous pattern at the group level. In total, six different motivational patterns were identified, three from English majors and three from L3 majors. It was also interesting to identify that a few learners developed a type of multilingually oriented motivation during their L3 learning. Data collected at the second phase of fieldwork revealed that the intervention was effective in helping English majors to construct their ideal L3 selves but less useful in the case of L3 majors. At the individual level, six cases were analysed in depth to investigate how the trajectories identified at the group level developed temporally and contextually. The analysis shows that the construction of these learners' L3 motivation involved a complex interplay between their future L3 selves and current L3 learning experience. It was through this process that learners explored the relationship between the L3 and their self-identification, and attempted to develop their personal meaning of learning an L3. On the basis of the empirical evidence, this thesis argues that the construction of learners' L3 motivation hinges on exploration of the position of the L3 in their self-identification, and that class intervention might help learners to realise the importance of learning an L3 by helping them to develop their ideal L3 selves, at least in the case of non-L3-major students. Moreover, this study suggests that it is crucial for L3 learners in China to recognise the value of being multilingual, which plays an essential role in constructing their L3 selves and sustaining their L3 motivation.

This is a longitudinal study that aimed to explore the planning and preparation, and experiences of post-school transition of young people with learning disabilities in both, mainstream and special schools within one local authority in Scotland. Data were drawn from semi-structured interviews with the young people, parents and professionals, and also from questionnaire with parents, at three different stages, covering a period from the final year at school, up to the first year at college. In addition, observation was undertaken of two review meetings in one special school. The results found that despite all young people’s post-school destination being college, they went through a variety of experiences, suggesting that a different approach needs to be taken to planning and preparation to ensure a smooth and seamless transition. The study revealed that despite many improvements, there was still a lack of information about the post-school provisions for the young people among the school staff and other professionals. The study proposes that the role of parents is as important as the role of the school staff. The study also makes some recommendations for future research, policy and practice.

Stability of diagnosis, symptoms and functioning across the life span is central to understanding any disorder and yet remains a relatively unexplored area in the study of autism (Sigman & McGovern, 2005). This is particularly apparent in the development of communication, including social interaction and language development in children with autism spectrum disorder (ASD), as there is little research on longitudinal development of children with ASD in general. The outlook on ASD has changed throughout the years, and although the emphasis on speech delay and communication problems have been separated from ASD, it is still one of the most common causes of initial referral in autism diagnoses (Pickles, Risi & Lord, 2004). Understanding the trajectory of communication for a child with ASD is fundamental in providing support and intervention in early years development. As communication is also a primary indicator on later development, it can gage outcomes into adaptive skills, school achievement and adult independence in later adult life. Eleven articles were identified in order to systematically review longitudinal studies based on communication development in ASD, or lack thereof, and why it is important to further carry out research in this area. This review seeks to explore: 1. How the development of different communicative functions in children with ASD is related to change over time. And, 2. What aspects of the child’s proximal processes and/or the child’s characteristics are discussed during measurement periods. Communicative functions were the most common form of communication observed in the studies at assessment periods and as for time points; two assessment periods were most common showing a linear trajectory of progress or decline from time point 1 and 2. All studies discussed aspects of child characteristics, most predominantly being gender and I.Q., however lacked insight into the significance of these and factors of proximal process during measurement periods in the studies reviewed. Ultimately, results display a need for more studies with at least three time points. With two time points only comes a “before” and “after” perspective, whereas, three or more time points enables collection of waves of data, showing key predictors of change in communication in children with a form of ASD.