abstract: As urban populations become increasingly dense, massive amounts of new 'big' data that characterize human activity are being made available and may be characterized as having a large volume of observations, being produced in real-time or near real-time, and including a diverse variety of information. In particular, spatial interaction (SI) data - a collection of human interactions across a set of origins and destination locations - present unique challenges for distilling big data into insight. Therefore, this dissertation identifies some of the potential and pitfalls associated with new sources of big SI data. It also evaluates methods for modeling SI to investigate the relationships that drive SI processes in order to focus on human behavior rather than data description. A critical review of the existing SI modeling paradigms is first presented, which also highlights features of big data that are particular to SI data. Next, a simulation experiment is carried out to evaluate three different statistical modeling frameworks for SI data that are supported by different underlying conceptual frameworks. Then, two approaches are taken to identify the potential and pitfalls associated with two newer sources of data from New York City - bike-share cycling trips and taxi trips. The first approach builds a model of commuting behavior using a traditional census data set and then compares the results for the same model when it is applied to these newer data sources. The second approach examines how the increased temporal resolution of big SI data may be incorporated into SI models. Several important results are obtained through this research. First, it is demonstrated that different SI models account for different types of spatial effects and that the Competing Destination framework seems to be the most robust for capturing spatial structure effects. Second, newer sources of big SI data are shown to be very useful for complimenting traditional sources of data, though they are not sufficient substitutions. Finally, it is demonstrated that the increased temporal resolution of new data sources may usher in a new era of SI modeling that allows us to better understand the dynamics of human behavior. / Dissertation/Thesis / Doctoral Dissertation Geography 2017

O estudo da distribuição de pragas em espaço e tempo em sistemas agrícolas fornece informação importante sobre os mecanismos de dispersão das espécies e sua interação com fatores ambientais. Esse tipo de estudos também é de muita ajuda no desenvolvimento de planos de amostragem, na otimização de programas de manejo integrado de pragas e no planejamento de experimentos. O objetivo deste trabalho foi comparar vários modelos hierárquicos na modelagem da variação espaço-temporal da infestação da broca do café visando produzir mapas de risco da infestação que descrevam adequadamente o processo de infestação. Foram usadas diferentes combinações de efeitos aleatórios representando variabilidade não estruturada, com diferentes escolhas de distribuições a priori para os parâmetros e os hiperparâmetros dos modelos. Foram também usados diferentes esquemas de vizinhança para representar a correlação espacial dos dados. O ajuste dos modelos foi feito usando métodos MCMC. A estatística deviance e funções de perda quadrática foram usadas para a comparação entre modelos. Os resultados são apresentados como uma seqüência de mapas de risco de infestação. / Study of agricultural pests distribution in space and time provides important information about the species dispersion mechanisms and its interaction with environmental factors. It also helps the development of sampling plans, the integrated pest management and planning of experiments. The aim of this work was to compare several hierarchical models in modelling the spatio-temporal variation of the coffee berry borer infestation in order to produce risk maps. Different combinations of random effects representing spatially structured and unstructured variability were used, with different prior distributions for the parameters and hyperparameters. Also different neighbourhood schemes were used to represent the spatial correlation of the data. The model fitting was done using MCMC methods and deviance and squared loss function were used for the comparison between models. The results are presented as a sequence of risk maps.

Tese (livre-docencia) - Universidade Estadual de Campinas, Instituto de Geociencias / Made available in DSpace on 2018-08-04T14:43:27Z (GMT). No. of bitstreams: 1 Ferreira_MarcosCesar_LD.pdf: 11039567 bytes, checksum: 211ed0a607b655ff110573325fda72eb (MD5) Previous issue date: 2003 / Resumo: Este estudo apresenta um procedimento metodológico baseado em sistema de informação geográfica, para modelagem cartográfica e análise regional de dados epidemiológicos relacionados a doenças tropicais, utilizando como exemplo uma epidemia de dengue. A proposta apóia-se nos paradigmas da escola espacial da Geografia sintetizados no conceito de mapemática, que reúne em uma mesma abordagem espaço-tempo, a cartografia temática e a análise espacial aplicada em SIG. Tomou-se como universo de ensaio, a epidemia de dengue ocorrida em 2001 no noroeste do Estado de São Paulo, que infectou a população de municípios da mesoregião de São José do Rio Preto, cujos contextos espacial e epidemiológico, serviram de objeto para a experimentação do procedimento metodológico aqui proposto. Em síntese, o procedimento adotado baseia-se na fusão de dois paradigmas de investigação espacial: a modelagem do espaço da epidemia em objetos exatos e campos contínuos e a modelagem do [empo da epidemia nas dimensões escalares monotemporal e multitemporal. Estas categorias espaço-tempo são combinadas entre si, gerando-se quatro níveis de analise espacial e construção de mapas epidemiológicos. No nível monotemporal-objeto, os mapas elucidam a espacialidade da epidemia, evidenciando clusters, contágios espaciais entre municípios e anomalias locacionais de incidência. No nível multítemporal-objeto, utilizando-se sequencia mento cartotemporal, os mapas mostram a dinâmica espacial dos casos por municípios, segundo as categorias casos novos, casos mantidos e casos extintos durante a evolução da epidemia. Já na categoria monotemporai-campo, a epidemia é abordada em modelos digitais isopléticos, sem a segmentação do espaço em limites municipais, evidenciando a forma e a orientação preferencial de manchas na forma de nuvens de probabilidade de incidência da doença. Ainda sob esta categoria espaço-tempo, são construídos mapas de superfícies de mostrando a regionalização da epidemia, desprezando-se as variações locais e elucidando-se tendências predominantes em escalas menores. Na categoria multemporal-campos, é estudada a difusão espacial da epidemia em seqüências isopléticas espaço-tempo, e sintetizadas em mapas de vetores de mobilidade espacial do centro geográfico da epidemia. A fase final e sintética do procedimento apresentado trata-se da análise da difusão espacial da epidemia segundo o modelo de redes geográficas. Nesta etapa da investigação, são construídos mapas de nodalidade e de potencial de contágio entre núcleos urbanos por via rodoviária, adotando-se como referência modelos clássicos de acessibilidade e hierarquia urbana. O do procedimento inclui ainda, a análise estatística baseada na cartografia de probabilidades, seguindo-se os modelos de Poisson e Lambert-Gauss, e a análise comparativa entre mapas de indicadores da epidemia e mapas de indicadores socioeconômicos, buscando-se esclarecer, possíveis associações e correlações entre incidência de casos e variáveis demográficas e urbanas de municípios afetados pela enfermidade / Abstract: This study presents a methodology for cartographic modeling and regional analysis of dengue fever epidemics, based on spatial analysis techniques and geographical information system. Data from 109 counties organized in epidemiological weeks about a dengue fever epidemic occurred in 2001 in northwest of Sao Paulo state, were used to map incidence and spatial diffusion of cases. The methodology is based on a five levels approach: four levels, adding exact objects/continuous fields models and single/multiple times slices sequences, and a fifth level, based in network analysis of counties connection and disease probabilities mapping. At single time scale/exacts objects level, county clusters, spatial contagious of counties and local incidence rates were mapped. At multiple time scale/exacts objects level, spatial dynamics of the cases it was mapped in spatio-time sequencing model. Using the single time/continuous field level isoplethic and tendency surface maps it was produced. At the multiple times/continuous field level, spatial diffusion maps and spatial-time mobility of mean geographical center of dengue epidemics it were designed using a sequential maps model. At the last level of methodology, urban nodes connection are spatially analyzed using network road analysis techniques, to map potential of contagious between counties, spatial dispersion of epidemics between counties and the spread path of dengue over region as a whole / Tese (livre-docencia) - Univer / Livre-Docente em Geografia

Abstract Type 1 diabetes mellitus (T1DM) among children is of a particular importance in Finland, where its incidence is the highest in the world and still increasing. However, the aetiology of T1DM is not fully known. According to current knowledge, both genetic and environmental factors operate together, leading to an attack by the immune system on the insulin-producing beta cells. The purpose of this study was to investigate the geographical variation in the incidence of T1DM among children aged up to 14 years in Finland. Geographical Information Systems (GIS) and Bayesian spatial statistics were applied in a search for unusual spatial patterns and risk factor associations. The incidence of T1DM among children aged up to 14 years showed clear geographical variations in Finland. Living in a rural environment increased the risk for T1DM, and the risk was particularly high among children living in rural heartland areas. There was no association between the variation in T1DM incidence and the zinc and nitrate concentrations of drinking water. A male excess in the incidence of T1DM was seen in the low-incidence areas. The geographical variation in the risk of T1DM was marked only among children aged up to 9 years. Because genetics is a necessary but not a sufficient cause of T1DM, it could be hypothesized that there are some thus far unknown environmental risk factors affecting particularly younger children in Finland. Some of those factors may be related to a rural environment. The geographical variation in the M/F ratio of T1DM was a challenging observation and warrants more analytical study.

abstract: Spatial regression is one of the central topics in spatial statistics. Based on the goals, interpretation or prediction, spatial regression models can be classified into two categories, linear mixed regression models and nonlinear regression models. This dissertation explored these models and their real world applications. New methods and models were proposed to overcome the challenges in practice. There are three major parts in the dissertation. In the first part, nonlinear regression models were embedded into a multistage workflow to predict the spatial abundance of reef fish species in the Gulf of Mexico. There were two challenges, zero-inflated data and out of sample prediction. The methods and models in the workflow could effectively handle the zero-inflated sampling data without strong assumptions. Three strategies were proposed to solve the out of sample prediction problem. The results and discussions showed that the nonlinear prediction had the advantages of high accuracy, low bias and well-performed in multi-resolution. In the second part, a two-stage spatial regression model was proposed for analyzing soil carbon stock (SOC) data. In the first stage, there was a spatial linear mixed model that captured the linear and stationary effects. In the second stage, a generalized additive model was used to explain the nonlinear and nonstationary effects. The results illustrated that the two-stage model had good interpretability in understanding the effect of covariates, meanwhile, it kept high prediction accuracy which is competitive to the popular machine learning models, like, random forest, xgboost and support vector machine. A new nonlinear regression model, Gaussian process BART (Bayesian additive regression tree), was proposed in the third part. Combining advantages in both BART and Gaussian process, the model could capture the nonlinear effects of both observed and latent covariates. To develop the model, first, the traditional BART was generalized to accommodate correlated errors. Then, the failure of likelihood based Markov chain Monte Carlo (MCMC) in parameter estimating was discussed. Based on the idea of analysis of variation, back comparing and tuning range, were proposed to tackle this failure. Finally, effectiveness of the new model was examined by experiments on both simulation and real data. / Dissertation/Thesis / Doctoral Dissertation Statistics 2020

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / The emergence and development of electronic health records have contributed to an abundance of patient data that can greatly be used and analyzed to promote health outcomes and even eliminate health disparities. However, challenges exist in the data received with factors such as data inconsistencies, accuracy issues, and unstructured formatting being evident. Furthermore, the current electronic health records and clinical information systems that are present do not contain the social determinants of health that may enhance our understanding of the characteristics and mechanisms of disease risk and transmission as well as health disparities research. Linkage to external population health databases to incorporate these social determinants of health is often necessary. This study provides an opportunity to identify and analyze health disparities using geographical information systems on two important sexually transmitted diseases in chlamydia and gonorrhea using Marion County, Indiana as the geographical location of interest. Population health data from the Social Assets and Vulnerabilities Indicators community information system and electronic health record data from the Indiana Network for Patient Care will be merged to measure the distribution and variability of greatest chlamydia and gonorrhea risk and to determine where the greatest areas of health disparities exist. A series of both statistical and spatial statistical methods such as a longitudinal measurement of health disparity through the Gini index, a hot-spot and cluster analysis, and a geographically weighted regression will be conducted in this study. The outcome and broader impact of this research will contribute to enhanced surveillance and increased effective strategies in identifying the level of health disparities for sexually transmitted diseases in vulnerable localities and high-risk communities. Additionally, the findings from this study will lead to improved standardization and accuracy in data collection to facilitate subsequent studies involving multiple disparate data sources. Finally, this study will likely introduce ideas for potential social determinants of health to be incorporated into electronic health records and clinical information systems.

Saudi Arabia has been trying to change its long tradition of relying on fossil fuels and seek renewable energy sources such as wind power. In this thesis, I firstly provide a comprehensive assessment of wind energy resources and associated spatio-temporal patterns over Saudi Arabia in both current and future climate conditions, based on a Regional Climate Model output. A high wind energy potential exists and is likely to persist at least until 2050 over a vast area ofWestern Saudi Arabia, particularly in the region between Medina and the Red Sea coast and during Summer months. Since an accurate assessment of wind extremes is crucial for risk management purposes, I then present the first high-resolution risk assessment of wind extremes over Saudi Arabia. Under the Bayesian framework, I measure the uncertainty of return levels and produce risk maps of wind extremes, which show that locations in the South of Saudi Arabia and near the Red Sea and the Persian Gulf are at very high risk of disruption of wind turbine operations. In order to perform spatial predictions of the bivariate wind random field for efficient turbine control, I propose parametric variogram matrix (function) models for cokriging, which have the advantage of allowing for a smooth transition between a joint second-order and intrinsically stationary vector random field. Under Gaussianity, the covariance function is central to spatio-temporal modeling, which is useful to understand the dynamics of winds in space and time. I review the various space-time covariance structures and models, some of which are visualized with animations, and associated tests. I also discuss inference issues and a case study based on a high-resolution wind-speed dataset. The Gaussian assumption commonly made in statistics needs to be validated, and I show that tests for independently and identically distributed data cannot be used directly for spatial data. I then propose a new multivariate test for spatial data by accounting for the spatial dependence. The new test is easy to compute, has a chi-square null distribution, and has a good control of the type I error and a high empirical power.

京都大学 / 0048 / 新制・課程博士 / 博士(医学) / 甲第18174号 / 医博第3894号 / 新制||医||1003(附属図書館) / 31032 / 京都大学大学院医学研究科医学専攻 / (主査)教授 金子 武嗣, 教授 髙橋 良輔, 教授 河野 憲二 / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DFAM

京都大学 / 0048 / 新制・課程博士 / 博士(医学) / 甲第18854号 / 医博第3965号 / 新制||医||1007(附属図書館) / 31805 / 京都大学大学院医学研究科医学専攻 / (主査)教授 古川 壽亮, 教授 髙橋 良輔, 教授 富樫 かおり / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DFAM