Multi-View Weighted Network

Extensive investigation has been conducted on network data, especially weighted network in the form of symmetric matrices with discrete count entries. Motivated by statistical inference on multi-view weighted network structure, this paper proposes a Poisson-Gamma latent factor model, not only separating view-shared and view-specific spaces but also achieving reduced dimensionality. A multiplicative gamma process shrinkage prior is implemented to avoid over parameterization and efficient full conditional conjugate posterior for Gibbs sampling is accomplished. By the accommodating of view-shared and view-specific parameters, flexible adaptability is provided according to the extents of similarity across view-specific space. Accuracy and efficiency are tested by simulated experiment. An application on real soccer network data is also proposed to illustrate the model.

Robust Uncertainty Quantification and Scalable Computation for Computer Models with Massive Output

Uncertainty quantification (UQ) is both an old and new concept. The current novelty lies in the interactions and synthesis of mathematical models, computer experiments, statistics, field/real experiments, and probability theory, with a particular emphasize on the large-scale simulations by computer models. The challenges not only come from the complication of scientific questions, but also from the size of the information. It is the focus in this thesis to provide statistical models that are scalable to massive data produced in computer experiments and real experiments, through fast and robust statistical inference.

Chapter 2 provides a practical approach for simultaneously emulating/approximating massive number of functions, with the application on hazard quantification of Soufri\`{e}re Hills volcano in Montserrate island. Chapter 3 discusses another problem with massive data, in which the number of observations of a function is large. An exact algorithm that is linear in time is developed for the problem of interpolation of Methylation levels. Chapter 4 and Chapter 5 are both about the robust inference of the models. Chapter 4 provides a new criteria robustness parameter estimation criteria and several ways of inference have been shown to satisfy such criteria. Chapter 5 develops a new prior that satisfies some more criteria and is thus proposed to use in practice.

Methods for Confounding Adjustment and High-Dimensional Environmental Exposures

Thesis (Ph.D.)--University of Washington, 2016-08

Principais fatores motivacionais na compra de livros de ficção

O presente projeto de Mestrado assenta no estudo dos principais fatores motivacionais na compra de livros de ficção, aprofundando a dicotomia uso próprio versus oferta, englobando duas perspetivas complementares: a sustentação bibliográfica e uma pesquisa quantitativa que foi concretizada através da distribuição de um inquérito por questionário, em formato digital, que permitiu obter 487 respostas válidas e completas. Os dados obtidos foram tratados no SPSS (Statistical Package for the Social Sciences), utilizando análises descritivas, que foram complementadas com técnicas de inferência estatística. Os resultados permitiram concluir que, apesar de homens e mulheres oferecerem um número idêntico de livros, as mulheres compram e leem mais. Além disso, cerca de um terço dos livros comprados destina-se a oferta. Ficou ainda provado que a interação com os autores nas redes sociais apresenta uma associação positiva com a importância atribuida a esse fator na hora de comprar o(s) livro(s). As mulheres são mais sensíveis às “Políticas de Marketing” (Atendimento Personalizado; Facilidade de Pagamento; Local com Cartão de Fidelização; Preços e Descontos; Elevada quantidade de livros), enquanto critérios de seleção do local de compra. Importa referir que a compra é concretizada de forma menos impulsiva quando o livro é para oferta. Os atributos da capa mais relevantes no processo de decisão de compra são o “Título” e a “Sinopse”. Contudo, os diferentes fatores da capa estudados não apresentam diferenças significativas na compra para uso próprio comparativamente à oferta, no que respeita à sua importância. “Autores com prémios literários” e “Nobel” e “Ser uma novidade” (livro) são outros fatores (não da capa) que apresentam diferenças significativas favoráveis à compra para oferta. Por outro lado, “Recomendação de Amigos e Familiares” e “Presença/Ligação/Interação com o Autor nas redes sociais” são mais favoráveis à compra para uso próprio. As conclusões são relevantes para enquadrar as preferências dos consumidores, possibilitando aos profissionais do marketing algumas referências para definir estratégias que respondam às suas necessidades e ambições. Além disso, ao explorar a dimensão dos submercados (Uso próprio versus Oferta), será possível ir ao encontro das exigências dos compradores, tornando a subjetividade da aquisição/utilização numa ferramenta eficaz da própria idealização e personalização dos livros, permitindo conceber e implementar ideias empreendedoras que visem estimular a compra e, consequentemente, melhorar os hábitos de leitura de todos os portugueses.

Optimal static and sequential design : a critical review

The aim of this thesis is to review and augment the theory and methods of optimal experimental design. In Chapter I the scene is set by considering the possible aims of an experimenter prior to an experiment, the statistical methods one might use to achieve those aims and how experimental design might aid this procedure. It is indicated that, given a criterion for design, a priori optimal design will only be possible in certain instances and, otherwise, some form of sequential procedure would seem to be indicated. In Chapter 2 an exact experimental design problem is formulated mathematically and is compared with its continuous analogue. Motivation is provided for the solution of this continuous problem, and the remainder of the chapter concerns this problem. A necessary and sufficient condition for optimality of a design measure is given. Problems which might arise in testing this condition are discussed, in particular with respect to possible non-differentiability of the criterion function at the design being tested. Several examples are given of optimal designs which may be found analytically and which illustrate the points discussed earlier in the chapter. In Chapter 3 numerical methods of solution of the continuous optimal design problem are reviewed. A new algorithm is presented with illustrations of how it should be used in practice. It is shown that, for reasonably large sample size, continuously optimal designs may be approximated to well by an exact design. In situations where this is not satisfactory algorithms for improvement of this design are reviewed. Chapter 4 consists of a discussion of sequentially designed experiments, with regard to both the philosophies underlying, and the application of the methods of, statistical inference. In Chapter 5 we criticise constructively previous suggestions for fully sequential design procedures. Alternative suggestions are made along with conjectures as to how these might improve performance. Chapter 6 presents a simulation study, the aim of which is to investigate the conjectures of Chapter 5. The results of this study provide empirical support for these conjectures. In Chapter 7 examples are analysed. These suggest aids to sequential experimentation by means of reduction of the dimension of the design space and the possibility of experimenting semi-sequentially. Further examples are considered which stress the importance of the use of prior information in situations of this type. Finally we consider the design of experiments when semi-sequential experimentation is mandatory because of the necessity of taking batches of observations at the same time. In Chapter 8 we look at some of the assumptions which have been made and indicate what may go wrong where these assumptions no longer hold.

Fault detection with Conditional Gaussian Network

International audience

Data quality issues in the GIS modelling of air pollution and cardiovascular mortality in Bangalore

Cardiovascular disease (CVD) is the world's number one cause of mortality. Research in recent years has begun to illustrate a significant association between CVD and air pollution. As most of these studies employed traditional statistics, cross-sectional or meta-analysis methods, a study undertaken by the authors was designed to investigate how a geographical information system (GIS) could be used to develop a more efficient spatio-temporal method of analysis than the currently existing methods mainly based on statistical inference. Using Bangalore, India, as a case study, demographic, environmental and CVD mortality data was sought from the city. However, critical deficiencies in the quality of the environmental data and mortality records were identified and quantified. This paper discusses the shortcomings in the quality of mortality data, together with the development of a framework based on WHO guidelines to improve the defects, henceforth considerably improving data quality.

Study on Bivariate Normal Distribution

Let (X, Y) be bivariate normal random vectors which represent the responses as a result of Treatment 1 and Treatment 2. The statistical inference about the bivariate normal distribution parameters involving missing data with both treatment samples is considered. Assuming the correlation coefficient ρ of the bivariate population is known, the MLE of population means and variance (ξ, η, and σ2) are obtained. Inferences about these parameters are presented. Procedures of constructing confidence interval for the difference of population means ξ – η and testing hypothesis about ξ – η are established. The performances of the new estimators and testing procedure are compared numerically with the method proposed in Looney and Jones (2003) on the basis of extensive Monte Carlo simulation. Simulation studies indicate that the testing power of the method proposed in this thesis study is higher.

Buy three but get only two: The smallest effect in a 2 × 2 ANOVA is always uninterpretable

Loftus (Memory & Cognition 6:312-319, 1978) distinguished between interpretable and uninterpretable interactions. Uninterpretable interactions are ambiguous, because they may be due to two additive main effects (no interaction) and a nonlinear relationship between the (latent) outcome variable and its indicator. Interpretable interactions can only be due to the presence of a true interactive effect in the outcome variable, regardless of the relationship that it establishes with its indicator. In the present article, we first show that same problem can arise when an unmeasured mediator has a nonlinear effect on the measured outcome variable. Then we integrate Loftus's arguments with a seemingly contradictory approach to interactions suggested by Rosnow and Rosenthal (Psychological Bulletin 105:143-146, 1989). We show that entire data patterns, not just interaction effects alone, produce interpretable or noninterpretable interactions. Next, we show that the same problem of interpretability can apply to main effects. Lastly, we give concrete advice on what researchers can do to generate data patterns that provide unambiguous evidence for hypothesized interactions.

Using health-related quality of life instruments for children with long-term conditions : On the basis of a national quality registry system

Introduction: There has been a continuous development of new technologies in healthcare that are derived from national quality registries. However, this innovation needs to be translated into the workflow of healthcare delivery, to enable children with long-term conditions to get the best support possible to manage their health during everyday life. Since children living with long-term conditions experience different interference levels in their lives, healthcare professionals need to assess the impact of care on children’s day-to-day lives, as a complement to biomedical assessments. Aim: The overall aim of this thesis was to explore and describe the use of instruments about health-related quality of life (HRQOL) in outpatient care for children with long-term conditions on the basis of a national quality registry system. Methods: The research was conducted by using comparative, cross-sectional and explorative designs and data collection was performed by using different methods. The questionnaire DISABKIDS Chronic Generic Measure -37 was used as well as semi-structured interviews and video-recordings from consultations. Altogether, 156 children (8–18 years) and nine healthcare professionals participated in the studies. Children with Type 1 Diabetes (T1D) (n 131) answered the questionnaire DISABKIDS and children with rheumatic diseases, kidney diseases and T1D (n 25) were interviewed after their consultation at the outpatient clinic after the web-DISABKIDS had been used. In total, nine healthcare professionals used the HRQOL instrument as an assessment tool during the encounters which was video-recorded (n 21). Quantitative deductive content analysis was used to describe content in different HRQOL instruments. Statistical inference was used to analyse results from DISABKIDS and qualitative content analysis was used to analyse the interviews and video-recordings. Results: The findings showed that based on a biopsychosocial perspective, both generic and disease-specific instruments should be used to gain a comprehensive evaluation of the child’s HRQOL. The DISABKIDS instrument is applicable when describing different aspects of health concerning children with T1D. When DISABKIDS was used in the encounters, children expressed positive experiences about sharing their results with the healthcare professional. It was discovered that different approaches led to different outcomes for the child when the healthcare professionals were using DISABKIDS during the encounter. When an instructing approach is used, the child’s ability to learn more about their health and how to improve their health is limited. When an inviting or engaging approach is used by the professional, the child may become more involved during the conversations. Conclusions: It could be argued that instruments of HRQOL could be used as a complement to biomedical variables, to promote a biopsychosocial perspective on the child’s health. According to the children in this thesis, feedback on their results after answering to web-DISABKIDS is important, which implies that healthcare professionals need to prioritize time for discussions about results from HRQOL instruments in the encounters. If healthcare professionals involve the child in the discussion of the results of the HRQOL, misinterpreted answers could be corrected during the conversation. Concurrently, this claims that healthcare professionals invite and engage the child.

The Power of the Synthetic Control Method

The synthetic control method (SCM) is a new, popular method developed for the purpose of estimating the effect of an intervention when only one single unit has been exposed. Other similar, unexposed units are combined into a synthetic control unit intended to mimic the evolution in the exposed unit, had it not been subject to exposure. As the inference relies on only a single observational unit, the statistical inferential issue is a challenge. In this paper, we examine the statistical properties of the estimator, study a number of features potentially yielding uncertainty in the estimator, discuss the rationale for statistical inference in relation to SCM, and provide a Web-app for researchers to aid in their decision of whether SCM is powerful for a specific case study. We conclude that SCM is powerful with a limited number of controls in the donor pool and a fairly short pre-intervention time period. This holds as long as the parameter of interest is a parametric specification of the intervention effect, and the duration of post-intervention period is reasonably long, and the fit of the synthetic control unit to the exposed unit in the pre-intervention period is good.

Monte Carlo simulations and capital structure research

The evolution of the debt ratio under alternative types of managerialbehavior can generate non-standard leverage processes. This createsproblems for statistical inference in empirical capital structure research. We argue in this paper that when the data generating process is not standard, a useful way to evaluate the appropriateness of inferences and the empirical methodology is via Monte Carlo simulations that mimic the data generating process under alternative assumptions about managerial behavior. We illustrate with several examples.

Efectividad del tratamiento de lumbalgia con acupuntura

Se realizó un estudio observacional retrospectivo longitudinal en una Institución prestadora de Servicios de Salud de la ciudad de Bogotá, con el objetivo de evaluar la efectividad en el manejo del dolor de la terapia con acupuntura en el tratamiento de lumbalgia. Se tomaron 150 historias clínicas de pacientes con lumbalgia atendidos de enero de 2014 a mayo de 2016, las cuales fueron sometidas a los criterios de inclusión definidos por los autores, arrojando 48 historias sometidas a la prueba de Friedman con el fin de identificar el impacto sobre el dolor del tratamiento con acupuntura en los pacientes seleccionados. Adicionalmente, bajo un muestreo aleatorio simple de distribución normal sobre las 48 historias clínicas evaluadas, se seleccionaron 25 casos a los cuales se les aplicó una encuesta no estructurada, con el fin de obtener información sobre el estado de la patología después de finalizar el tratamiento e identificar las posibles causas de deserción. Con este estudio se concluye que la terapia con acupuntura es efectiva en el manejo del dolor de pacientes con lumbalgia, y que es necesario realizar más estudios que puedan sustentar la inclusión de la terapéutica en el manejo de esta patología.