Doctor of Philosophy / Department of Statistics / Haiyan Wang / High throughput screening technologies have generated a huge amount of biological data in the last ten years. With the easy availability of array technology, researchers started to investigate biological mechanisms using experiments with more sophisticated designs that pose novel challenges to statistical analysis. We provide theory for robust statistical tests in three flexible models. In the first model, we consider the hypothesis testing problems when there are a large number of variables observed repeatedly over time. A potential application is in tumor genomics where an array comparative genome hybridization (aCGH) study will be used to detect progressive DNA copy number changes in tumor development. In the second model, we consider hypothesis testing theory in a longitudinal microarray study when there are multiple treatments or experimental conditions. The tests developed can be used to detect treatment effects for a large group of genes and discover genes that respond to treatment over time. In the third model, we address a hypothesis testing problem that could arise when array data from different sources are to be integrated. We perform statistical tests by assuming a nested design. In all models, robust test statistics were constructed based on moment methods allowing unbalanced design and arbitrary heteroscedasticity. The limiting distributions were derived under the nonclassical setting when the number of probes is large. The test statistics are not targeted at a single probe. Instead, we are interested in testing for a selected set of probes simultaneously. Simulation studies were carried out to compare the proposed methods with some traditional tests using linear mixed-effects models and generalized estimating equations. Interesting results obtained with the proposed theory in two cancer genomic studies suggest that the new methods are promising for a wide range of biological applications with longitudinal arrays.

This thesis explores employment among people who inject drugs (IDU). It seeks identify what differentiates IDU who work from those who do not, barriers to labour market participation, and how employment is perceived and experienced by IDU. Using longitudinal data from the Vancouver Injection Drug User Study (VIDUS), it conducts this research through a detailed examination of the implications of missing data, quantitative analyses of transitions into employment and qualitative, in-depth interviews. Missing data analyses identified differences between those that those that do and do not have missing data, as well as predictors of observation gaps and how individuals end their study participation (either right-hand censorship, attrition, or death). Differences were observed along individual, behavioural and contextual dimensions. Analytical approaches to the relationship between data structure and content gleaned useful information for longitudinal studies with marginalized populations. Discrete time event history analyses of work transitions revealed complex relationships between drug use, drug-related activities, situational risk factors, and transitions into employment. While most IDU did not make transitions into employment, some did, and while some statistical relationships were expected, others were surprising. Novel findings included mode-specific addiction treatment impacts on employment (methadone vs. non-methadone) and the importance of the broader risk environment over and above even high-intensity substance use. Finally, qualitative interviews identified heterogeneity in individual motivations toward and experiences of work. Those who maintained concurrent drug use and formal labour market involvement utilized strategies to spatially and temporally separate the two activities. Individual capacities to employ these strategies were facilitated by material, vocational and temporal motivations, and interfered with by health conditions, catastrophic events and institutional relationships that operated as barriers to employment. This study provides insight into what is a known social determinant of health in the general population among injection drug users.

Thesis advisor: Ina V. S. Mullis / TIMSS and PIRLS assess representative samples of students at regular intervals, measuring trends in student achievement and student contexts for learning. Because individual students are not tracked over time, analysis of international large-scale assessment data is usually conducted cross-sectionally. Gustafsson (2007) proposed examining the data longitudinally by analyzing relationships between country-level trends in background constructs and trends in student achievement. Through longitudinal analysis of international large-scale assessment data, it becomes possible to mitigate some of the confounding factors in the analysis. This dissertation extends this country-level approach to subpopulations within countries. Adapting a pseudo-panel approach from the econometrics literature (Deaton, 1985), the proposed approach creates subpopulations by grouping students based on demographic characteristics, such as gender or parental education. Following grouping, the subpopulations with the same demographic characteristics are linked across cycles and the aggregated subpopulation means are treated as panel data and analyzed through longitudinal data analysis techniques. As demonstrated herein the primary advantages of the subpopulation approach are that it allows for analysis of subgroup differences, and it captures within-country relationships in the data that are not possible to analyze at country level. Illustrative analysis examines the relationship between early literacy activities and PIRLS reading achievement using PIRLS 2001 and PIRLS 2011 data. Results from the subpopulation approach are compared with student-level and country-level cross-sectional results as well as country-level longitudinal results. In addition, within-country analysis examines the subpopulation-level relationship between early literacy activities and PIRLS reading achievement, multiple group analysis compares regression coefficient estimates between boys and girls and across parental education subgroups, and mediation analysis examines the extent that partaking in early literacy activities can explain differences between boys and girls in PIRLS reading achievement. / Thesis (PhD) — Boston College, 2017. / Submitted to: Boston College. Lynch School of Education. / Discipline: Educational Research, Measurement and Evaluation.

This work offers a longitudinal analysis of the "Science" section in Lidove noviny in between years 1997-2012 as well as the theoretical background for science journalism in the Czech republic. In the theoretical part you will find discourse analysis for both of general journalism and science, which is completed with the description of science journalism which bridges the gap between the former two discourses. The analysis of science journalism and its forms in the Czech republic follows. Then the press title Lidove noviny and its "Science" section are presented. The latter part of this work concerns with the longitudinal analysis of this section, which is based on foreign studies as well as on the interview with Josef Matyas, the editor-in-chief of the "Science" section. Results of this analysis are put together with the theoretical expectations and some interesting questions for further examinations follow.

The scope of this thesis is to process and analyze statistically Magnetic Resonance Images (MR-T1) from Parkinson’s disease patients in order to detect brain areas that exhibit brain change which is caused by the disease. Parkinson’s disease is an idiopathic disease which means that its cause is yet unknown. It is a chronic neurodegenerative disorder of the central nervous system which causes the progressive death of specific brain neurons that leads to motor impairments (tremor, bradykinesia, muscle rigidity) and non motor ones (cognitive, sleep, sensation disturbances). Magnetic Resonance Images (T1-weighted) were acquired from both Parkinson’s patients and healthy subjects (Controls) at intervals of 0 and 5 years. The data have undergone longitudinal (two-time-point), cross sectional (single-time-point) and statistical analysis with the use of FSL software library. Evidence of atrophy among Parkinson’s patients aroused, in brain areas near the ventricles and the middle temporal gyrus, after statistical analysis / Ο σκοπός αυτής της εργασίας είναι η επεξεργασία και στατιστική ανάλυση μαγνητηκών τομογραφιών (MR-T1) από ασθενείς με Πάρκινσον για την ανίχνευση περιοχών του εγκεφάλου που παρουσιάζουν μεταβολές που οφείλονται στην ασθένεια. Η ασθένεια Πάρκινσον είναι ιδιοπαθής, δηλαδή ασθένεια της οποίας η αιτία παραμένει ακόμη άγνωστη. Είναι μια χρόνια δυσλειτουργία λόγω εκφυλισμού των νευρώνων του κεντρικού νευρικού συστήματος η οποία προκαλεί τη σταδιακή νεκρωση συγκεκριμένης ομάδας εγκεφαλικών νευρώνων. Αυτή η νέκρωση οδηγεί σε κινητικές δυσλειτουργίες (τρέμουλο, βραδυκινησία, και μυϊκή δυσκαμψία και σε μή κινητικές όπως γνωστικές, διαταραχής ύπνου,διαταραχές αφής κ.α. Μαγνητικές τομογραφίες (τύπου Τ1) ασθενών και υγιών ελήφθησαν σε διαστήματα 0 και 5 ετών. Τα δεδομένα αναλύθηκαν με δυο μεθόδους (longitudinal και cross-sectional) και εν συνεχεία έγινε στατιστική επεξεργασία των αποτελεσμάτων. Έγινε χρήση της βιβλιοθήκης FSL Μετά από στατιστική ανάλυση προέκυψαν ενδείξεις ατροφίας στους ασθενείς με Πάρκινσον σε περιοχές του εγεκφάλου κοντά στις εγκεφαλικές κοιλίες (ventricles) και στη μέσο-κροταφική έλικα (middle temporal gyrus).

Os benefícios que a Tecnologia da Informação (TI) tem trazido à sociedade e às organizações vem aumentado ao longo do tempo. A TI tem se desenvolvido com uma rapidez muito grande, prometendo ganhos de eficiência e aumentos na produtividade das empresas. Nos últimos anos, inúmeras organizações têm investido altas quantias em TI, independentemente do setor em que atuam. Dentro deste contexto, observa-se que o setor bancário tem se destacado, pois os recursos destinados para investimentos em TI crescem em ritmo acelerado. Entretanto, a falta de boas medidas quantitativas para mensurar o impacto destes investimentos na produtividade dificulta sua comprovação. Desta forma, fazem-se necessários estudos que apliquem métodos de análise temporal dos investimentos em TI, já que este tipo de investimento não apresenta resultado imediato. Buscando sanar esta lacuna, este trabalho utilizou a metodologia Análise Envoltória de Dados (DEA), que visa analisar eficiência de instituições homogêneas de forma relativa. A partir desta técnica, buscou-se analisar o efeito das variações dos investimentos em TI de um ano para outro nas variações da eficiência relativa dessas instituições em até quatro períodos seguintes ao investimento, visando identificar uma possível regularidade cíclica. Utilizou-se um banco de dados contendo treze anos de informações contábeis de 260 bancos em atuação no Brasil. Dentre as principais conclusões obtidas a partir do teste de diferenças de média, destaca-se que os aumentos dos Investimentos em TI de um ano para outro não são traduzidos em aumentos de eficiência no ano seguinte à sua realização, em nenhum dos três momentos de conversão estudados. Analisadas as defasagens temporais das variações das eficiências em dois, três e quatro anos após o incremento dos Investimentos em TI, percebeu-se que no momento de Conversão II, este foi traduzido em eficiência ao transformar Ativos em Receitas Líquidas. Já na Conversão Global, o período para reverter de forma direta, a variação dos investimentos em TI em variação de eficiência relativa, é de dois anos. A Conversão I, que representa a capacidade do banco ser competitivo, ao transformar Despesas em Ativos, não apresentou significância nos intervalos de tempo analisados no estudo. / The benefits brought by Information Technology (IT) to the society and to organizations have increased over time. IT has been developed very quickly, promising companies’ increases in efficiency and productivity. Lately, many organizations have invested great sums in IT, regardless of the sector in which they operate. Within this context, the banking sector has gain a prominent position, since its resources in IT investments grow at an accelerated rhythm. However, the lack of good quantitative measures to mensurate the impact of these investments on productivity complicates its evidence. Thus, studies that apply temporal analysis methods of IT investments become necessary, since this type of investment does not show immediate results. Trying to heal this gap, this study has used the Data Envelopment Analysis (DEA) methodology which aims to analyze the efficiency of homogeneous institutions in a relative way. With this technique, the effect of the variation in IT spending from one year to another in the variations of relative efficiency of these institutions has been analyzed up to four periods following the investment, in order to identify a possible cyclical regularity. A database containing thirteen years of accounting information from 260 banks in operation in Brazil was used. Among the main results from the mean differences test, deserves attention the fact that in none of the three stages of conversion studied increases in IT investments from one year to another are translated into increases in efficiency in the years following its implementation. Analyzed the temporal discrepancies of the changes in efficiencies in two, three and four years after the increase of IT investments, it was noticed that at the time of Conversion II, this has been translated into efficiency to transform Assets in Revenues. However, in the Global Conversion the period to directly reverse the variation in IT investments in variation of relative efficiency is two years. Representing the bank's ability to be competitive, Conversion I showed no significance when Expenses were turns into Assets in the time intervals analyzed in this study.

Os benefícios que a Tecnologia da Informação (TI) tem trazido à sociedade e às organizações vem aumentado ao longo do tempo. A TI tem se desenvolvido com uma rapidez muito grande, prometendo ganhos de eficiência e aumentos na produtividade das empresas. Nos últimos anos, inúmeras organizações têm investido altas quantias em TI, independentemente do setor em que atuam. Dentro deste contexto, observa-se que o setor bancário tem se destacado, pois os recursos destinados para investimentos em TI crescem em ritmo acelerado. Entretanto, a falta de boas medidas quantitativas para mensurar o impacto destes investimentos na produtividade dificulta sua comprovação. Desta forma, fazem-se necessários estudos que apliquem métodos de análise temporal dos investimentos em TI, já que este tipo de investimento não apresenta resultado imediato. Buscando sanar esta lacuna, este trabalho utilizou a metodologia Análise Envoltória de Dados (DEA), que visa analisar eficiência de instituições homogêneas de forma relativa. A partir desta técnica, buscou-se analisar o efeito das variações dos investimentos em TI de um ano para outro nas variações da eficiência relativa dessas instituições em até quatro períodos seguintes ao investimento, visando identificar uma possível regularidade cíclica. Utilizou-se um banco de dados contendo treze anos de informações contábeis de 260 bancos em atuação no Brasil. Dentre as principais conclusões obtidas a partir do teste de diferenças de média, destaca-se que os aumentos dos Investimentos em TI de um ano para outro não são traduzidos em aumentos de eficiência no ano seguinte à sua realização, em nenhum dos três momentos de conversão estudados. Analisadas as defasagens temporais das variações das eficiências em dois, três e quatro anos após o incremento dos Investimentos em TI, percebeu-se que no momento de Conversão II, este foi traduzido em eficiência ao transformar Ativos em Receitas Líquidas. Já na Conversão Global, o período para reverter de forma direta, a variação dos investimentos em TI em variação de eficiência relativa, é de dois anos. A Conversão I, que representa a capacidade do banco ser competitivo, ao transformar Despesas em Ativos, não apresentou significância nos intervalos de tempo analisados no estudo. / The benefits brought by Information Technology (IT) to the society and to organizations have increased over time. IT has been developed very quickly, promising companies’ increases in efficiency and productivity. Lately, many organizations have invested great sums in IT, regardless of the sector in which they operate. Within this context, the banking sector has gain a prominent position, since its resources in IT investments grow at an accelerated rhythm. However, the lack of good quantitative measures to mensurate the impact of these investments on productivity complicates its evidence. Thus, studies that apply temporal analysis methods of IT investments become necessary, since this type of investment does not show immediate results. Trying to heal this gap, this study has used the Data Envelopment Analysis (DEA) methodology which aims to analyze the efficiency of homogeneous institutions in a relative way. With this technique, the effect of the variation in IT spending from one year to another in the variations of relative efficiency of these institutions has been analyzed up to four periods following the investment, in order to identify a possible cyclical regularity. A database containing thirteen years of accounting information from 260 banks in operation in Brazil was used. Among the main results from the mean differences test, deserves attention the fact that in none of the three stages of conversion studied increases in IT investments from one year to another are translated into increases in efficiency in the years following its implementation. Analyzed the temporal discrepancies of the changes in efficiencies in two, three and four years after the increase of IT investments, it was noticed that at the time of Conversion II, this has been translated into efficiency to transform Assets in Revenues. However, in the Global Conversion the period to directly reverse the variation in IT investments in variation of relative efficiency is two years. Representing the bank's ability to be competitive, Conversion I showed no significance when Expenses were turns into Assets in the time intervals analyzed in this study.

Os benefícios que a Tecnologia da Informação (TI) tem trazido à sociedade e às organizações vem aumentado ao longo do tempo. A TI tem se desenvolvido com uma rapidez muito grande, prometendo ganhos de eficiência e aumentos na produtividade das empresas. Nos últimos anos, inúmeras organizações têm investido altas quantias em TI, independentemente do setor em que atuam. Dentro deste contexto, observa-se que o setor bancário tem se destacado, pois os recursos destinados para investimentos em TI crescem em ritmo acelerado. Entretanto, a falta de boas medidas quantitativas para mensurar o impacto destes investimentos na produtividade dificulta sua comprovação. Desta forma, fazem-se necessários estudos que apliquem métodos de análise temporal dos investimentos em TI, já que este tipo de investimento não apresenta resultado imediato. Buscando sanar esta lacuna, este trabalho utilizou a metodologia Análise Envoltória de Dados (DEA), que visa analisar eficiência de instituições homogêneas de forma relativa. A partir desta técnica, buscou-se analisar o efeito das variações dos investimentos em TI de um ano para outro nas variações da eficiência relativa dessas instituições em até quatro períodos seguintes ao investimento, visando identificar uma possível regularidade cíclica. Utilizou-se um banco de dados contendo treze anos de informações contábeis de 260 bancos em atuação no Brasil. Dentre as principais conclusões obtidas a partir do teste de diferenças de média, destaca-se que os aumentos dos Investimentos em TI de um ano para outro não são traduzidos em aumentos de eficiência no ano seguinte à sua realização, em nenhum dos três momentos de conversão estudados. Analisadas as defasagens temporais das variações das eficiências em dois, três e quatro anos após o incremento dos Investimentos em TI, percebeu-se que no momento de Conversão II, este foi traduzido em eficiência ao transformar Ativos em Receitas Líquidas. Já na Conversão Global, o período para reverter de forma direta, a variação dos investimentos em TI em variação de eficiência relativa, é de dois anos. A Conversão I, que representa a capacidade do banco ser competitivo, ao transformar Despesas em Ativos, não apresentou significância nos intervalos de tempo analisados no estudo. / The benefits brought by Information Technology (IT) to the society and to organizations have increased over time. IT has been developed very quickly, promising companies’ increases in efficiency and productivity. Lately, many organizations have invested great sums in IT, regardless of the sector in which they operate. Within this context, the banking sector has gain a prominent position, since its resources in IT investments grow at an accelerated rhythm. However, the lack of good quantitative measures to mensurate the impact of these investments on productivity complicates its evidence. Thus, studies that apply temporal analysis methods of IT investments become necessary, since this type of investment does not show immediate results. Trying to heal this gap, this study has used the Data Envelopment Analysis (DEA) methodology which aims to analyze the efficiency of homogeneous institutions in a relative way. With this technique, the effect of the variation in IT spending from one year to another in the variations of relative efficiency of these institutions has been analyzed up to four periods following the investment, in order to identify a possible cyclical regularity. A database containing thirteen years of accounting information from 260 banks in operation in Brazil was used. Among the main results from the mean differences test, deserves attention the fact that in none of the three stages of conversion studied increases in IT investments from one year to another are translated into increases in efficiency in the years following its implementation. Analyzed the temporal discrepancies of the changes in efficiencies in two, three and four years after the increase of IT investments, it was noticed that at the time of Conversion II, this has been translated into efficiency to transform Assets in Revenues. However, in the Global Conversion the period to directly reverse the variation in IT investments in variation of relative efficiency is two years. Representing the bank's ability to be competitive, Conversion I showed no significance when Expenses were turns into Assets in the time intervals analyzed in this study.

Children who have survived a brain tumor often experience late consequences as a result of the tumor itself, and/or treatment. The child’s ability to engage in daily activities may be restricted by these late consequences. Examples of these late consequences are challenges with their activity levels and engagement in daily activities. Therefore, it is important to study these children’s late consequences over time. The aim of the thesis is to use data from medical and school records linked to ICF, to investigate how the participation problems/ restrictions of children that completed cancer directed treatment for a brain tumor tend to occur simultaneously with codes from other ICF components, over time. For the present research the inclusion criteria were children that were followed by the habilitation service, school and health care for at least 4 years after completing their brain tumor treatment. Seven children were included in the study. For each child, records were obtained from habilitation, school and health care and a complete retrospective screening was conducted between February 2022 and April 2022. Problems in relation to everyday life were identified and linked to ICF codes and domains. Descriptive statistics was used to analyze the data, in order to see the re-occurrences of the ICF domains during the time and observe the trajectory and intensity of the problems. The results revealed that the problems linked to body functions were the most frequently mentioned ICF domain by all three services as well as over time. Problems over time related to activity and participation were less focused and little emphasis were focused on problems related to the environment. The pattern over time was very individual. In order to more prominent focus on the child’s everyday functioning, follow-up guidelines should also include the child's functioning in everyday life, and not only areas related to body function. To conclude, when caring for these children, it is important to also focus on the child’s function in everyday life and to individualize the care since the pattern of problems over time seems to be very individual. / <p></p><p></p> / Using ICF to Describe Problems With Functioning in Everyday Life for Children Who Completed Treatment for Brain Tumor: An Analysis Based on Professionals' Documentation

Les travaux présentés concernent essentiellement l’étude de certains déterminants sociaux des consommations d’alcool. Il s’agit d’analyser comment certains aspects des circonstances de vie, de travail et l’environnement social peuvent influencer ce comportement et modifier les consommations d’alcool au cours du temps.Ces analyses ont été menées dans la cohorte Gazel, composée de plus de 20 000 sujets(15 000 hommes et 5 000 femmes) employés d’EDF‐GDF et âgés de 35 à 50 ans à l’inclusion en 1989. Les déterminants étudiés sont les conditions de travail, le statut marital des femmes et les changements de statut au cours de la vie, ainsi que le passage à la retraite.Globalement, on observe que l’environnement professionnel, familial et social sont des déterminants de l’évolution des habitudes de consommation, et jouent un rôle souvent socialement différencié, les différentes catégories sociales ne se comportant habituellement pas de la même façon dans des situations comparables. / This thesis is about the social determinants of alcohol consumption. More specifically, the aims were to study how some circumstances of life, working and social environment may exert an influence on changes in drinking behaviours over time.The analyses were conducted within the Gazel cohort, including more than 20 000 subjects(15 000 men and 5 000 women) employees of EDF‐GDF, the French national utility company,aged 35‐50 at the inception of the cohort in 1989, which were followed‐up since that period.The main determinants that were studied are the working conditions, the marital status of women, and retirement. The main findings showed that the occupational, familial and social environment play a role in the changes in drinking behaviours over time, and that their effects are socially patterned,