Mixture of time-dependent growth models with an application to blue swimmer crab length-frequency data

Understanding how aquatic species grow is fundamental in fisheries because stock assessment often relies on growth dependent statistical models. Length-frequency-based methods become important when more applicable data for growth model estimation are either not available or very expensive. In this article, we develop a new framework for growth estimation from length-frequency data using a generalized von Bertalanffy growth model (VBGM) framework that allows for time-dependent covariates to be incorporated. A finite mixture of normal distributions is used to model the length-frequency cohorts of each month with the means constrained to follow a VBGM. The variances of the finite mixture components are constrained to be a function of mean length, reducing the number of parameters and allowing for an estimate of the variance at any length. To optimize the likelihood, we use a minorization–maximization (MM) algorithm with a Nelder–Mead sub-step. This work was motivated by the decline in catches of the blue swimmer crab (BSC) (Portunus armatus) off the east coast of Queensland, Australia. We test the method with a simulation study and then apply it to the BSC fishery data.

Statistical modeling of protein lysate array data

The protein lysate array is an emerging technology for quantifying the protein concentration ratios in multiple biological samples. It is gaining popularity, and has the potential to answer questions about post-translational modifications and protein pathway relationships. Statistical inference for a parametric quantification procedure has been inadequately addressed in the literature, mainly due to two challenges: the increasing dimension of the parameter space and the need to account for dependence in the data. Each chapter of this thesis addresses one of these issues. In Chapter 1, an introduction to the protein lysate array quantification is presented, followed by the motivations and goals for this thesis work. In Chapter 2, we develop a multi-step procedure for the Sigmoidal models, ensuring consistent estimation of the concentration level with full asymptotic efficiency. The results obtained in this chapter justify inferential procedures based on large-sample approximations. Simulation studies and real data analysis are used to illustrate the performance of the proposed method in finite-samples. The multi-step procedure is simpler in both theory and computation than the single-step least squares method that has been used in current practice. In Chapter 3, we introduce a new model to account for the dependence structure of the errors by a nonlinear mixed effects model. We consider a method to approximate the maximum likelihood estimator of all the parameters. Using the simulation studies on various error structures, we show that for data with non-i.i.d. errors the proposed method leads to more accurate estimates and better confidence intervals than the existing single-step least squares method.

Data-Aware Scheduling in Datacenters

Datacenters have emerged as the dominant form of computing infrastructure over the last two decades. The tremendous increase in the requirements of data analysis has led to a proportional increase in power consumption and datacenters are now one of the fastest growing electricity consumers in the United States. Another rising concern is the loss of throughput due to network congestion. Scheduling models that do not explicitly account for data placement may lead to a transfer of large amounts of data over the network causing unacceptable delays. In this dissertation, we study different scheduling models that are inspired by the dual objectives of minimizing energy costs and network congestion in a datacenter. As datacenters are equipped to handle peak workloads, the average server utilization in most datacenters is very low. As a result, one can achieve huge energy savings by selectively shutting down machines when demand is low. In this dissertation, we introduce the network-aware machine activation problem to find a schedule that simultaneously minimizes the number of machines necessary and the congestion incurred in the network. Our model significantly generalizes well-studied combinatorial optimization problems such as hard-capacitated hypergraph covering and is thus strongly NP-hard. As a result, we focus on finding good approximation algorithms. Data-parallel computation frameworks such as MapReduce have popularized the design of applications that require a large amount of communication between different machines. Efficient scheduling of these communication demands is essential to guarantee efficient execution of the different applications. In the second part of the thesis, we study the approximability of the co-flow scheduling problem that has been recently introduced to capture these application-level demands. Finally, we also study the question, "In what order should one process jobs?'' Often, precedence constraints specify a partial order over the set of jobs and the objective is to find suitable schedules that satisfy the partial order. However, in the presence of hard deadline constraints, it may be impossible to find a schedule that satisfies all precedence constraints. In this thesis we formalize different variants of job scheduling with soft precedence constraints and conduct the first systematic study of these problems.

Usefulness of social tagging in organizing and providing access to the web: An analysis of indexing consistency and quality

This dissertation research points out major challenging problems with current Knowledge Organization (KO) systems, such as subject gateways or web directories: (1) the current systems use traditional knowledge organization systems based on controlled vocabulary which is not very well suited to web resources, and (2) information is organized by professionals not by users, which means it does not reflect intuitively and instantaneously expressed users’ current needs. In order to explore users’ needs, I examined social tags which are user-generated uncontrolled vocabulary. As investment in professionally-developed subject gateways and web directories diminishes (support for both BUBL and Intute, examined in this study, is being discontinued), understanding characteristics of social tagging becomes even more critical. Several researchers have discussed social tagging behavior and its usefulness for classification or retrieval; however, further research is needed to qualitatively and quantitatively investigate social tagging in order to verify its quality and benefit. This research particularly examined the indexing consistency of social tagging in comparison to professional indexing to examine the quality and efficacy of tagging. The data analysis was divided into three phases: analysis of indexing consistency, analysis of tagging effectiveness, and analysis of tag attributes. Most indexing consistency studies have been conducted with a small number of professional indexers, and they tended to exclude users. Furthermore, the studies mainly have focused on physical library collections. This dissertation research bridged these gaps by (1) extending the scope of resources to various web documents indexed by users and (2) employing the Information Retrieval (IR) Vector Space Model (VSM) - based indexing consistency method since it is suitable for dealing with a large number of indexers. As a second phase, an analysis of tagging effectiveness with tagging exhaustivity and tag specificity was conducted to ameliorate the drawbacks of consistency analysis based on only the quantitative measures of vocabulary matching. Finally, to investigate tagging pattern and behaviors, a content analysis on tag attributes was conducted based on the FRBR model. The findings revealed that there was greater consistency over all subjects among taggers compared to that for two groups of professionals. The analysis of tagging exhaustivity and tag specificity in relation to tagging effectiveness was conducted to ameliorate difficulties associated with limitations in the analysis of indexing consistency based on only the quantitative measures of vocabulary matching. Examination of exhaustivity and specificity of social tags provided insights into particular characteristics of tagging behavior and its variation across subjects. To further investigate the quality of tags, a Latent Semantic Analysis (LSA) was conducted to determine to what extent tags are conceptually related to professionals’ keywords and it was found that tags of higher specificity tended to have a higher semantic relatedness to professionals’ keywords. This leads to the conclusion that the term’s power as a differentiator is related to its semantic relatedness to documents. The findings on tag attributes identified the important bibliographic attributes of tags beyond describing subjects or topics of a document. The findings also showed that tags have essential attributes matching those defined in FRBR. Furthermore, in terms of specific subject areas, the findings originally identified that taggers exhibited different tagging behaviors representing distinctive features and tendencies on web documents characterizing digital heterogeneous media resources. These results have led to the conclusion that there should be an increased awareness of diverse user needs by subject in order to improve metadata in practical applications. This dissertation research is the first necessary step to utilize social tagging in digital information organization by verifying the quality and efficacy of social tagging. This dissertation research combined both quantitative (statistics) and qualitative (content analysis using FRBR) approaches to vocabulary analysis of tags which provided a more complete examination of the quality of tags. Through the detailed analysis of tag properties undertaken in this dissertation, we have a clearer understanding of the extent to which social tagging can be used to replace (and in some cases to improve upon) professional indexing.

Business model evolution and firm performance of entrepreneurial companies

This research explores the business model (BM) evolution process of entrepreneurial companies and investigates the relationship between BM evolution and firm performance. Recently, it has been increasingly recognised that the innovative design (and re-design) of BMs is crucial to the performance of entrepreneurial firms, as BM can be associated with superior value creation and competitive advantage. However, there has been limited theoretical and empirical evidence in relation to the micro-mechanisms behind the BM evolution process and the entrepreneurial outcomes of BM evolution. This research seeks to fill this gap by opening up the ‘black box’ of the BM evolution process, exploring the micro-patterns that facilitate the continuous shaping, changing, and renewing of BMs and examining how BM evolutions create and capture value in a dynamic manner. Drawing together the BM and strategic entrepreneurship literature, this research seeks to understand: (1) how and why companies introduce BM innovations and imitations; (2) how BM innovations and imitations interplay as patterns in the BM evolution process; and (3) how BM evolution patterns affect firm performances. This research adopts a longitudinal multiple case study design that focuses on the emerging phenomenon of BM evolution. Twelve entrepreneurial firms in the Chinese Online Group Buying (OGB) industry were selected for their continuous and intensive developments of BMs and their varying success rates in this highly competitive market. Two rounds of data collection were carried out between 2013 and 2014, which generates 31 interviews with founders/co-founders and in total 5,034 pages of data. Following a three-stage research framework, the data analysis begins by mapping the BM evolution process of the twelve companies and classifying the changes in the BMs into innovations and imitations. The second stage focuses down to the BM level, which addresses the BM evolution as a dynamic process by exploring how BM innovations and imitations unfold and interplay over time. The final stage focuses on the firm level, providing theoretical explanations as to the effects of BM evolution patterns on firm performance. This research provides new insights into the nature of BM evolution by elaborating on the missing link between BM dynamics and firm performance. The findings identify four patterns of BM evolution that have different effects on a firm’s short- and long-term performance. This research contributes to the BM literature by presenting what the BM evolution process actually looks like. Moreover, it takes a step towards the process theory of the interplay between BM innovations and imitations, which addresses the role of companies’ actions, and more importantly, reactions to the competitors. Insights are also given into how entrepreneurial companies achieve and sustain value creation and capture by successfully combining the BM evolution patterns. Finally, the findings on BM evolution contributes to the strategic entrepreneurship literature by increasing the understanding of how companies compete in a more dynamic and complex environment. It reveals that, the achievement of superior firm performance is more than a simple question of whether to innovate or imitate, but rather an integration of innovation and imitation strategies over time. This study concludes with a discussion of the findings and their implications for theory and practice.

Social Capital, HIV Risk Behavior and Substance Use among Recent Latino Immigrants in South Florida

Social capital, or social cohesion or group connectedness, can influence both HIV risk behavior and substance use. Because recent immigrants undergo a change in environment, one of the consequences can be a change in social capital. There may be an association among changes in social capital, and HIV risk behavior and substance use post immigration. The dissertation focused on the interface of these three variables among recent Latino immigrants (RLIs) in South Florida. The first manuscript is a systematic review of social capital and HIV risk behavior, and served as a partial background for the second and third manuscripts. Twelve papers with a measure of social capital as an independent variable and HIV risk as the dependent variable were included in the analysis. Eleven studies measured social capital at the individual level, and one study measured social capital at the group level. HIV risk was influenced by social capital, but the type of influence was dependent on the type of social capital and on the study population. Cognitive social capital, or levels of collective action, was protective against HIV in both men and women. The role of structural social capital, or levels of civic engagement/group participation, on HIV risk was dependent on the type of structural social capital and varied by gender. Microfinance programs and functional group participation were protective for women, while dysfunctional group participation and peer-level support may have increased HIV risk among men. The second manuscript was an original study assessing changes in social capital and HIV risk behavior pre to post immigration among RLIs in South Florida (n=527). HIV risk behavior was assessed through the frequency of vaginal-penile condom use, and the number of sexual partners. It was a longitudinal study using secondary data analysis to assess changes in social capital and HIV risk behavior pre immigration to two years post immigration, and to determine if there was a relationship between the two variables. There was an 8% decrease in total social capital (p ˂ .05). Reporting of ‘Never use’ of condoms in the past 90 days increased in all subcategories (p ˂ .05). Single men had a decrease in number of sexual partners (p ˂ .05). Lower social capital measured on the dimension of ‘friend and other’ was marginally associated with fewer sexual partners. The third manuscript was another original study looking at the association between social capital and substance use among RLIs in South Florida (n=527). Substance use with measured by frequency of hazardous alcoholic drinking, and illicit drug use. It was a longitudinal study of social capital and substance-use from pre to two years post immigration. Post-immigration, social capital, hazardous drinking and illicit drug use decreased (p˂.001). After adjusting for time, compared to males, females were less likely to engage in hazardous drinking (OR=.31, p˂.001), and less likely to engage in illicit drug use (OR=.67, p=.01). Documentation status was a moderator between social capital and illicit drug use. ‘Business’ and ‘Agency’ social capital were associated with changes in illicit drug use for documented immigrants. After adjusting for gender and marital status, on average, documented immigrants with a one-unit increase in ‘business’ social capital were 1.2 times more likely to engage in illicit drug use (p˂.01), and documented immigrants with one-unit increase in ‘agency’ social capital were 38% less likely to engage in illicit drug use (p˂.01). ‘Friend and other’ social capital was associated with a decrease in illicit drug use among undocumented immigrants. After adjusting for gender and marital status, on average, undocumented immigrants with a one-unit increase in ‘friend and other’ social capital were 45% less likely to engage in hazardous drinking and 44% less likely to use illicit drugs (p˂.01, p˂.05). Studying these three domains is relevant because HIV continues to be a public health issue, particularly in Miami-Dade County, which is ranked among other U.S. regions with high rates of HIV/AIDS prevalence. Substance use is associated with HIV risk behavior; in most studies, increased substance use is associated with increased chances of HIV risk behavior. Immigration, which is the hypothesized catalyst for the change in social capital, has an impact on the dynamic of a society. Greater immigration can be burdensome on the host country’s societal resources; however immigrants are also potentially a source of additional skilled labor for the workforce. Therefore, successful adaption of immigrants can have a positive influence on receiving communities. With Florida being a major receiver of immigrants to the U.S, this dissertation attempts to address an important public health issue for South Florida and the U.S. at large.

User interaction monitoring and analysis framework

An overview is given of a user interaction monitoring and analysis framework called BaranC. Monitoring and analysing human-digital interaction is an essential part of developing a user model as the basis for investigating user experience. The primary human-digital interaction, such as on a laptop or smartphone, is best understood and modelled in the wider context of the user and their environment. The BaranC framework provides monitoring and analysis capabilities that not only records all user interaction with a digital device (e.g. smartphone), but also collects all available context data (such as from sensors in the digital device itself, a fitness band or a smart appliances). The data collected by BaranC is recorded as a User Digital Imprint (UDI) which is, in effect, the user model and provides the basis for data analysis. BaranC provides functionality that is useful for user experience studies, user interface design evaluation, and providing user assistance services. An important concern for personal data is privacy, and the framework gives the user full control over the monitoring, storing and sharing of their data.

Patologías lumbares: determinación de los factores ocupacionales y carga prestacional en una entidad promotora de salud en Bogotá

Resumen: Introducción El dolor lumbar es un trastorno músculo esquelético que afecta la parte baja de la espalda, considerado como un problema de salud pública y catalogado como un desastre en el sitio de trabajo, se encuentra en las 10 primeras causas de enfermedad profesional reportadas por las entidades prestadoras de servicios de salud, generando ausentismo y discapacidad laboral en los países industrializados, con costos que oscilan de los 20 mil a los 98 millones de dólares en los Estados Unidos. Objetivo Determinar la prevalencia de patologías lumbares calificadas y sus factores ocupacionales asociados en una entidad promotora de salud de Bogotá Colombia durante 2013 al 2014. Metodología Se realizó un estudio de corte transversal con datos secundarios pertenecientes a 318 pacientes de una entidad promotora de salud en la ciudad de Bogotá que fueron diagnosticados con patologías lumbares (lumbalgia-lumbago, discopatía lumbar, trastorno de disco intervertebral, espondilolistesis, espondilólisis, hernia discal), y remitidos a medicina laboral o solicitaron calificación de origen en primera oportunidad, en el periodo comprendido entre el año 2013 al 2014. Las variables incluidas fueron sociodemográficas, ocupacionales y diagnósticos médicos, específicamente patologías lumbares. Se realizó distribuciones de frecuencias, medidas de tendencia central y dispersión, análisis de asociación mediante la prueba Chi cuadrado de Pearson y un análisis multivariado a través del modelo de regresión binaria logística y el análisis de concordancia usando el índice de Kappa. Para las pruebas se utilizó un nivel de significación de 0,05. Se digitó y depuró en SPSS versión 23. Resultado El total de usuarios diagnosticados con patologías lumbares fue de 318 de los cuales el 57,2% fueron de sexo masculino con edad promedio de 43 años (D.E 7,9 años). Se encontró asociación significativa entre lumbalgia y movimientos de columna lumbar y levantamiento de carga (p<0,05); discopatía lumbar y movimientos de columna lumbar y factores multicausales (p<0,05); trastorno de disco intervertebral y factores multicausales (p<0.05), hernia de disco y levantamiento de cargas (p<0,05). Respecto a espondilolistesis y espondilólisis no se encontró asociación con ningún factor de riesgo, pero si se encontró asociación significativa entre origen y movimientos de columna lumbar (p= 0.010), con postura mantenida (p= 0.014), con causas multifactoriales (p= 0.000). El grado de concordancia entre la entidad promotora de salud y la administradora de riesgos laborales arrojó un valor en el índice de kappa de 0.432 (p= 0.000) correspondiendo a un grado de acuerdo moderado; para la concordancia entre la entidad promotora de salud y la junta de calificación el índice de kappa fue de 0.680 (p= 0.000) grado de acuerdo alto. Conclusión Las patologías lumbares tienen un alta prevalencia en la población trabajadora como en la no trabajadora, encontrándose un gran número de factores condicionantes a estas enfermedades generando altos costos en días perdidos laborales y en días de incapacidad: Por lo tanto, es importante determinar si estas son catalogadas de origen común o de origen laboral, para establecer programas de vigilancia epidemiológica y programas preventivos.

Imaginarios sociales de adolescentes y docentes en torno al cuerpo, la corporalidad y la actividad física. Estudio cualitativo en un colegio de Bogotá, 2014-2015.

Problema. Esta investigación se aproxima al entorno escolar con el propósito de avanzar en la comprensión de los imaginarios de los adolescentes y docentes en torno al cuerpo, la corporalidad y la AF, como un elemento relevante en el diseño de programas y planes efectivos para fomento de la práctica de AF. Objetivo. Analizar los imaginarios sociales de docentes y adolescentes en torno a los conceptos de cuerpo, corporalidad y AF. Métodos. Investigación de corte cualitativo, descriptivo e interpretativo. Se realizaron entrevistas semi-estructuradas a docentes y a estudiantes entre los 12 y 18 años de un colegio público de Bogotá. Se realizó análisis de contenido. Se compararon los resultados de estudiantes por grupos de edades y género. Resultados. Docentes y estudiantes definen el cuerpo a partir de las características biológicas, las diferencias sexuales y las funciones vitales. La definición de corporalidad en los estudiantes se encuentra ligada con la imagen y la apariencia física; los docentes la entienden como la posibilidad de interactuar con el entorno y como la materialización de la existencia. La AF en los estudiantes se asocia con la práctica de ejercicio y deporte, en los docentes se comprende como una práctica de autocuidado que permite el mantenimiento de la salud. Conclusiones. Para promover la AF tempranamente como una experiencia vital es necesario intervenir los espacios escolares. Hay que vincular al cuerpo a los procesos formativos con el propósito de desarrollar la autonomía corporal, este aspecto implica cambios en los currículos.

Asociación de las violencias física, sexual y comunitaria con el embarazo en adolescentes: análisis multinivel

Objetivos Determinar si existe asociación entre la exposición a violencia, experimentada a nivel individual o municipal, y el embarazo adolescente en mujeres Colombianas entre 13 y 19 años de edad que contestaron la Encuesta de Demografía y Salud en el año 2010. Métodos Estudio de corte transversal, nacional y multinivel. Se tomaron datos de dos niveles jerárquicos: Nivel- 1: Datos individuales de una muestra representativa de 13.313 mujeres entre 13 y 19 años de edad provenientes de La Encuesta Nacional de Demografía y Salud del año 2010 y Nivel- 2: Datos municipales de 258 municipios provenientes de las estadísticas vitales del DANE. Resultados La prevalencia del embarazo adolescente fue del 16.8% IC 95% [16.2-17.4]. El análisis mostró que la asociación entre embarazo adolescente y violencia tanto individual, representada como violencia sexual [OR= 6.99 IC99% 4.80-10.10] y violencia física [OR= 1.74 IC99% 1.47-2.05] así como la violencia municipal medida con tasas de homicidios altas [OR= 1.99 IC99% 1.29-3.07] y muy altas [OR= 2.10 IC99% 1.21-3.61] se mantuvo estadísticamente significativa después de ajustar por las variables: Edad [OR= 1.81 IC99% 1.71-1.91], ocupación [OR= 1.62 IC99% 1.37-1.93], educación primaria o sin educación [OR= 2.20 IC99% 1.47-3.30], educación secundaria [OR= 1.70 IC99% 1.24-2.32], asistir al colegio [OR= 0.18 IC99% 0.15-0.21], conocimiento en la fisiología reproductiva [OR= 1.28 IC99% 1.06-1.54], el índice de riqueza Q1, Q2, Q3 [OR= 2.18 IC99% 1.42-3.34], [OR= 2.00 IC99% 1.39-2.28], [OR= 1.82 IC99% 1.92-2.25] y alto porcentaje de Necesidades básicas insatisfechas a nivel municipal [OR= 2.34 IC99% 1.55-3.52]. Conclusiones Este estudio mostró una relación significativamente estadística entre la violencia sexual y física con el inicio de relaciones sexuales y embarazo adolescente después de controlar por factores sociodemográficos y conocimientos en reproducción sexual en mujeres colombianas de 13 a 19 años en el año 2010. Esta asociación debe continuar siendo estudiada para lograr optimizar las estrategias de prevención y disminuir la tasa actual de embarazos adolescentes en el país y sus consecuencias.

Acoso laboral y sus efectos en la salud del trabajador : revisión de la literatura

Introducción: Desde los años 80 se viene haciendo énfasis en el acoso laboral, conocido en otros países como Mobbing, describiéndose como una forma de abuso y violencia psicológica en el lugar de trabajo, realizado ya sea por una sola persona o por un grupo de personas y que por sus implicaciones se estima de alto impacto para los trabajadores, y las organizaciones. Considerando la importancia y prevalencia del mobbing en la sociedad actual, se convierte en un tema relevante para el área de salud ocupacional. Objetivo: El objetivo de este estudio fue identificar los efectos del acoso laboral generados en la salud del trabajador. Metodología: Se realizó una revisión sistemática utilizando el método PRISMA, de las publicaciones vigentes entre los años 2006 a 2016 sobre los efectos del acoso laboral en la salud del trabajador. En la búsqueda se obtuvieron 778 artículos de los cuales 27 cumplían con los criterios de inclusión. Resultados: se encontró que la prevalencia del acoso laboral puede ser diferente de acuerdo a la definición utilizada, instrumento de medida y población estudiada, la cual fluctúa entre el 7% al 88% según el estudio analizado. Además se evidenció que la prevalencia también difiere dependiendo de quién sea el perpetrador del acoso, si el líder o jefe es el acosador es mayor (60,3%) que cuando es causado por colegas o por clientes (41,5%). El impacto del acoso laboral, según la mayoría de los estudios, es que provoca efectos negativos en la salud emocional del trabajador siendo la depresión una de las principales consecuencias con una relación estadísticamente significativa (p<0,001). Las enfermedades del aparato respiratorio y del sistema musculo esquelético y del tejido conectivo fueron las que se presentaron con mayor frecuencia en los trabajadores que sufren de acoso con un 43,5% y un 37.8% respectivamente. Conclusiones: éstos resultados demuestran que el acoso laboral no solamente es un problema desde el punto de vista organizacional, sino que conlleva consecuencias en la salud mental y física de los trabajadores que lo sufren. Palabras clave: Mobbing, workplace, acoso laboral, acoso psicológico, bullying, harassment, salud ocupacional, occupational health.

Ethical Perspectives on Big Data in Agri-food: Ownership and Governance for Safety

Big data are reshaping the way we interact with technology, thus fostering new applications to increase the safety-assessment of foods. An extraordinary amount of information is analysed using machine learning approaches aimed at detecting the existence or predicting the likelihood of future risks. Food business operators have to share the results of these analyses when applying to place on the market regulated products, whereas agri-food safety agencies (including the European Food Safety Authority) are exploring new avenues to increase the accuracy of their evaluations by processing Big data. Such an informational endowment brings with it opportunities and risks correlated to the extraction of meaningful inferences from data. However, conflicting interests and tensions among the involved entities - the industry, food safety agencies, and consumers - hinder the finding of shared methods to steer the processing of Big data in a sound, transparent and trustworthy way. A recent reform in the EU sectoral legislation, the lack of trust and the presence of a considerable number of stakeholders highlight the need of ethical contributions aimed at steering the development and the deployment of Big data applications. Moreover, Artificial Intelligence guidelines and charters published by European Union institutions and Member States have to be discussed in light of applied contexts, including the one at stake. This thesis aims to contribute to these goals by discussing what principles should be put forward when processing Big data in the context of agri-food safety-risk assessment. The research focuses on two interviewed topics - data ownership and data governance - by evaluating how the regulatory framework addresses the challenges raised by Big data analysis in these domains. The outcome of the project is a tentative Roadmap aimed to identify the principles to be observed when processing Big data in this domain and their possible implementations.

Methods for Biodata Analysis in different Omic Contexts

The world of Computational Biology and Bioinformatics presently integrates many different expertise, including computer science and electronic engineering. A major aim in Data Science is the development and tuning of specific computational approaches to interpret the complexity of Biology. Molecular biologists and medical doctors heavily rely on an interdisciplinary expert capable of understanding the biological background to apply algorithms for finding optimal solutions to their problems. With this problem-solving orientation, I was involved in two basic research fields: Cancer Genomics and Enzyme Proteomics. For this reason, what I developed and implemented can be considered a general effort to help data analysis both in Cancer Genomics and in Enzyme Proteomics, focusing on enzymes which catalyse all the biochemical reactions in cells. Specifically, as to Cancer Genomics I contributed to the characterization of intratumoral immune microenvironment in gastrointestinal stromal tumours (GISTs) correlating immune cell population levels with tumour subtypes. I was involved in the setup of strategies for the evaluation and standardization of different approaches for fusion transcript detection in sarcomas that can be applied in routine diagnostic. This was part of a coordinated effort of the Sarcoma working group of "Alleanza Contro il Cancro". As to Enzyme Proteomics, I generated a derived database collecting all the human proteins and enzymes which are known to be associated to genetic disease. I curated the data search in freely available databases such as PDB, UniProt, Humsavar, Clinvar and I was responsible of searching, updating, and handling the information content, and computing statistics. I also developed a web server, BENZ, which allows researchers to annotate an enzyme sequence with the corresponding Enzyme Commission number, the important feature fully describing the catalysed reaction. More to this, I greatly contributed to the characterization of the enzyme-genetic disease association, for a better classification of the metabolic genetic diseases.

Assessing the fit of unidimensional IRT models for binary data under model misspecification

Model misspecification affects the classical test statistics used to assess the fit of the Item Response Theory (IRT) models. Robust tests have been derived under model misspecification, as the Generalized Lagrange Multiplier and Hausman tests, but their use has not been largely explored in the IRT framework. In the first part of the thesis, we introduce the Generalized Lagrange Multiplier test to detect differential item response functioning in IRT models for binary data under model misspecification. By means of a simulation study and a real data analysis, we compare its performance with the classical Lagrange Multiplier test, computed using the Hessian and the cross-product matrix, and the Generalized Jackknife Score test. The power of these tests is computed empirically and asymptotically. The misspecifications considered are local dependence among items and non-normal distribution of the latent variable. The results highlight that, under mild model misspecification, all tests have good performance while, under strong model misspecification, the performance of the tests deteriorates. None of the tests considered show an overall superior performance than the others. In the second part of the thesis, we extend the Generalized Hausman test to detect non-normality of the latent variable distribution. To build the test, we consider a seminonparametric-IRT model, that assumes a more flexible latent variable distribution. By means of a simulation study and two real applications, we compare the performance of the Generalized Hausman test with the M2 limited information goodness-of-fit test and the Likelihood-Ratio test. Additionally, the information criteria are computed. The Generalized Hausman test has a better performance than the Likelihood-Ratio test in terms of Type I error rates and the M2 test in terms of power. The performance of the Generalized Hausman test and the information criteria deteriorates when the sample size is small and with a few items.