Bayesian approaches to the regression analysis for longitudinal measurements are considered. The history of measurements from a subject may convey characteristics of the subject. Hence, in a regression analysis with longitudinal measurements, the characteristics of each subject can be served as covariates, in addition to possible other covariates. Also, the longitudinal measurements may lead to complicated covariance structures within each subject and they should be modeled properly. When covariates are some unobservable characteristics of each subject, Bayesian parametric and nonparametric regressions have been considered. Although covariates are not observable directly, by virtue of longitudinal measurements, the covariates can be estimated. In this case, the measurement error problem is inevitable. Hence, a classical measurement error model is established. In the Bayesian framework, the regression function as well as all the unobservable covariates and nuisance parameters are estimated. As multiple covariates are involved, a generalized additive model is adopted, and the Bayesian backfitting algorithm is utilized for each component of the additive model. For the binary response, the logistic regression has been proposed, where the link function is estimated by the Bayesian parametric and nonparametric regressions. For the link function, introduction of latent variables make the computing fast. In the next part, each subject is assumed to be observed not at the prespecifiedtime-points. Furthermore, the time of next measurement from a subject is supposed to be dependent on the previous measurement history of the subject. For this outcome- dependent follow-up times, various modeling options and the associated analyses have been examined to investigate how outcome-dependent follow-up times affect the estimation, within the frameworks of Bayesian parametric and nonparametric regressions. Correlation structures of outcomes are based on different correlation coefficients for different subjects. First, by assuming a Poisson process for the follow- up times, regression models have been constructed. To interpret the subject-specific random effects, more flexible models are considered by introducing a latent variable for the subject-specific random effect and a survival distribution for the follow-up times. The performance of each model has been evaluated by utilizing Bayesian model assessments.

The performance of a manufacturing system relies on its four types of elements: operators, machines, computer system and material handling system. To ensure the performance of these elements, operational data containing various aspects of information are collected for monitoring and analysis. This dissertation focuses on the operator performance evaluation and machine failure prediction. The proposed research work is motivated by the following challenges in analyzing operational data. (i) the complex relationship between the variables, (ii) the implicit information important to failure prediction, and (iii) data with outliers, missing and erroneous measurements. To overcome these challenges, the following research has been conducted. To compare operator performance, a methodology combining regression modeling and multiple comparisons technique is proposed. The regression model quantifies and removes the complex effects of other impacting factors on the operator performance. A robust zero-inflated Poisson (ZIP) model is developed to reduce the impacts of the excessive zeros and outliers in the performance metric, i.e. the number of defects (NoD), on regression analysis. The model residuals are plotted in non-parametric statistical charts for performance comparison. The estimated model coefficients are also used to identify under-performing machines. To detect temporal patterns from operational data sequence, an algorithm is proposed for detecting interval-based asynchronous periodic patterns (APP). The algorithm effectively and efficiently detects pattern through a modified clustering and a convolution-based template matching method. To predict machine failures based on the covariates with erroneous measurements, a new method is proposed for statistical inference of proportional hazard model under a mixture of classical and Berkson errors. The method estimates the model coefficients with an expectation-maximization (EM) algorithm with expectation step achieved by Monte Carlo simulation. The model estimated with the proposed method will improve the accuracy of the inference on machine failure probability. The research work presented in this dissertation provides a package of solutions to improve manufacturing system performance. The effectiveness and efficiency of the proposed methodologies have been demonstrated and justified with both numerical simulations and real-world case studies.

Correlated data frequently arise from epidemiological studies, especially familial and longitudinal studies. Longitudinal design has been used by researchers to investigate the changes of certain characteristics over time at the individual level as well as how potential factors influence the changes. Familial studies are often designed to investigate the dependence of health conditions among family members. Various models have been developed for this type of multivariate data, and a wide variety of estimation techniques have been proposed. However, data collected from observational studies are often far from perfect, as measurement error may arise from different sources such as defective measuring systems, diagnostic tests without gold references, and self-reports. Under such scenarios only rough surrogate variables are measured. Measurement error in covariates in various regression models has been discussed extensively in the literature. It is well known that naive approaches ignoring covariate error often lead to inconsistent estimators for model parameters. In this thesis, we develop inferential procedures for analyzing correlated data with response measurement error. We consider three scenarios: (i) likelihood-based inferences for generalized linear mixed models when the continuous response is subject to nonlinear measurement errors; (ii) estimating equations methods for binary responses with misclassifications; and (iii) estimating equations methods for ordinal responses when the response variable and categorical/ordinal covariates are subject to misclassifications. The first problem arises when the continuous response variable is difficult to measure. When the true response is defined as the long-term average of measurements, a single measurement is considered as an error-contaminated surrogate. We focus on generalized linear mixed models with nonlinear response error and study the induced bias in naive estimates. We propose likelihood-based methods that can yield consistent and efficient estimators for both fixed-effects and variance parameters. Results of simulation studies and analysis of a data set from the Framingham Heart Study are presented. Marginal models have been widely used for correlated binary, categorical, and ordinal data. The regression parameters characterize the marginal mean of a single outcome, without conditioning on other outcomes or unobserved random effects. The generalized estimating equations (GEE) approach, introduced by Liang and Zeger (1986), only models the first two moments of the responses with associations being treated as nuisance characteristics. For some clustered studies especially familial studies, however, the association structure may be of scientific interest. With binary data Prentice (1988) proposed additional estimating equations that allow one to model pairwise correlations. We consider marginal models for correlated binary data with misclassified responses. We develop “corrected” estimating equations approaches that can yield consistent estimators for both mean and association parameters. The idea is related to Nakamura (1990) that is originally developed for correcting bias induced by additive covariate measurement error under generalized linear models. Our approaches can also handle correlated misclassifications rather than a simple misclassification process as considered by Neuhaus (2002) for clustered binary data under generalized linear mixed models. We extend our methods and further develop marginal approaches for analysis of longitudinal ordinal data with misclassification in both responses and categorical covariates. Simulation studies show that our proposed methods perform very well under a variety of scenarios. Results from application of the proposed methods to real data are presented. Measurement error can be coupled with many other features in the data, e.g., complex survey designs, that can complicate inferential procedures. We explore combining survey weights and misclassification in ordinal covariates in logistic regression analyses. We propose an approach that incorporates survey weights into estimating equations to yield design-based unbiased estimators. In the final part of the thesis we outline some directions for future work, such as transition models and semiparametric models for longitudinal data with both incomplete observations and measurement error. Missing data is another common feature in applications. Developing novel statistical techniques for dealing with both missing data and measurement error can be beneficial.

No description available.

Degradation of components and structures is a major threat to the safety and reliability of large engineering systems, such as the railway networks or the nuclear power plants. Periodic inspection and maintenance are thus required to ensure that the system is in good condition for continued service. A key element for the optimal inspection and maintenance is to accurately model and forecast the degradation progress, such that inspection and preventive maintenance can be scheduled accordingly. In recently years, probabilistic models based on stochastic process have become increasingly popular in degradation modelling, due to their flexibility in modelling both the temporal and sample uncertainties of the degradation. However, because of the often complex structure of stochastic degradation models, accurate estimate of the model parameters can be quite difficult, especially when the inspection data are noisy or incomplete. Not considering the effect of uncertain inspection data is likely to result in biased parameter estimates and therefore erroneous predictions of future degradation. The main objective of the thesis is to develop formal methods for the parameter estimation of stochastic degradation models using uncertain inspection data. Three typical stochastic models are considered. They are the random rate model, the gamma process model and the Poisson process model, among which the random rate model and the gamma process model are used to model the flaw growth, and the Poisson process model is used to model the flaw generation. Likelihood functions of the three stochastic models given noisy or incomplete inspection data are derived, from which maximum likelihood estimates can be obtained. The thesis also investigates Bayesian inference of the stochastic degradation models. The most notable advantage of Bayesian inference over classical point estimates is its ability to incorporate background information in the estimation process, which is especially useful when inspection data are scarce. A major obstacle for accurate parameter inference of stochastic models from uncertain inspection data is the computational difficulties of the likelihood evaluation, as it often involves calculation of high dimensional integrals or large number of convolutions. To overcome the computational difficulties, a number of numerical methods are developed in the thesis. For example, for the gamma process model subject to sizing error, an efficient maximum likelihood method is developed using the Genz's transform and quasi-Monte Carlo simulation. A Markov Chain Monte Carlo simulation with sizing error as auxiliary variables is developed for the Poisson flaw generation model, A sequential Bayesian updating using approximate Bayesian computation and weighted samples is also developed for Bayesian inference of the gamma process subject to sizing error. Examples on the degradation of nuclear power plant components are presented to illustrate the use of the stochastic degradation models using practical uncertain inspection data. It is shown from the examples that the proposed methods are very effective in terms of accuracy and computational efficiency.

An abrupt interface between mountains and prairies in southwestern Alberta means wilderness areas and carnivore populations overlap cattle grazing lands. Consequently, there is concern about the effects of large carnivores, especially wolves, on livestock. I used GPS clusters and scat samples to determine year-round wolf diets in this region. Both methods indicated a significant seasonal shift in wolf diets from wild prey during the non-grazing season to cattle in the grazing season. The GPS cluster method effectively identified wolf kills but this method relies on telemetry with high accuracy and precision. In southwestern Alberta, Argos satellite radicollars have been used extensively by wildlife managers. I compare how differences in precision between GPS and Argos technologies affect the estimation of habitat-selection models. Differences in accuracy and precision can lead to erroneous conclusions about animal selection of habitat. / Ecology

Intra-dialytic haemodynamic instability is a common and disabling problem which may lead to morbidity and mortality though repeated organ ischaemia, but it has proven difficult to link any particular blood pressure threshold with hard patient outcomes. The relationship between blood pressure and downstream organ ischaemia during haemodialysis has not been well characterised. Previous attempts to predict and prevent intra-dialytic hypotension have had mixed results, partly due to patient and event heterogeneity. Using the brain as the indicator organ, we aimed to model the dynamic relationship between blood pressure, real-time symptoms, downstream organ ischaemia during haemodialysis, in order to identify the most physiologically grounded, prognostic definition of intra-dialytic decompensation. Following on from this, we aimed to predict the onset of intra-dialytic decompensation using personalised, probabilistic models of multivariate, continuous physiological data, ultimately working towards an early warning system for intra-dialytic adverse events. This was a prospective study of 60 prevalent haemodialysis patients who underwent extensive, continuous physiological monitoring of haemodynamic, cardiorespiratory, tissue oxygenation and dialysis machine parameters for 3-4 weeks. In addition, longitudinal cognitive function testing was performed at baseline and at 12 months. Despite their use in clinical practice, we found that blood pressure thresholds alone have a poor trade off between sensitivity and specificity for predicting downstream tissue ischaemia during haemodialysis. However, the performance of blood pressure thresholds could be improved by stratification for the presence or absence of cerebral autoregulation, and personalising thresholds according to the individual lower limit of autoregulation. For patients without autoregulation, the optimal blood pressure target was a mean arterial pressure (MAP) of 70mmHg. A key finding was that cumulative intra-dialytic exposure to cerebral ischaemia, but not to hypotension per se, corresponded to change in executive cognitive function over 12 months. Therefore we chose cerebral ischaemia as the definition of intra-dialytic decompensation for predictive modelling. We were able to demonstrate that the development of cerebral desaturation could be anticipated from earlier deviations of univariate physiological data from the expected trajectory for a given patient, but sensitivity was limited by the heterogeneity of events even within one individual. The most useful phys- iological data streams included peripheral saturation variance, cerebral saturation variance, heart rate and mean arterial pressure. Multivariate data fusion techniques using these variables created promising personalised models capable of giving an early warning of decompensation. Future work will involve the refinement and prospective testing of these models. In addition, we envisage a prospective study assessing the benefit of autoregulation-guided blood pressure targets on short term outcomes such as patient symptoms and wellbeing, as well as longer term outcomes such as cognitive function.

Submitted by Laura Pereira (laurasgualda@gmail.com) on 2018-04-15T15:39:39Z No. of bitstreams: 1 Dissertacao_LauraGualda_Bib.pdf: 1147862 bytes, checksum: 1ba34dfb1e02e555a66410badfb0cbb5 (MD5) / Approved for entry into archive by Janete de Oliveira Feitosa (janete.feitosa@fgv.br) on 2018-04-27T12:59:33Z (GMT) No. of bitstreams: 1 Dissertacao_LauraGualda_Bib.pdf: 1147862 bytes, checksum: 1ba34dfb1e02e555a66410badfb0cbb5 (MD5) / Made available in DSpace on 2018-05-08T14:43:18Z (GMT). No. of bitstreams: 1 Dissertacao_LauraGualda_Bib.pdf: 1147862 bytes, checksum: 1ba34dfb1e02e555a66410badfb0cbb5 (MD5) Previous issue date: 2018-03-26 / Quantitative studies aiming to disentangle public corruption effects often emphasize the lack of objective information in this research area. The CGU Random Audits Anti-Corruption Program, based on extensive and unadvertised audits of transfers from the federal government to municipalities, emerged as a potential source to try to fill this gap. Reports generated by these audits describe corrupt and mismanagement practices in detail, but reading and coding them manually is laborious and requires specialized people to do it. We propose a statistical framework to guide the use of text data to construct objective indicators of corruption and use it in inferential models. It consists of two main steps. In the first one, we use machine learning methods for text classification to create an indicator of corruption based on irregularities from audit reports. In the second step, we use this indicator in a regression model, accounting for the measurement error carried from the first step. To validate this framework, we replicate an empirical strategy presented by Ferraz et al. (2012) to estimate effects of corruption in educational funds on primary school students’ outcomes, between 2006 and 2015. We achieved an expected accuracy of 92% on the binary classification of irregularities, and our results endorse Ferraz et al.. findings: students in municipal schools perform significantly worse on standardized tests in municipalities where was found corruption in education. / Estudos quantitativos em corrupção política enfatizam a falta de informações objetivas nessa área de pesquisa. O Programa de Fiscalização por Sorteios Públicos da CGU se baseia em auditorias não anunciadas das transferências do Governo Federal para municípios, e aparece como uma potencial solução para essa lacuna. Relatórios gerados durante essas auditorias descrevem com detalhe práticas de corrupção e de má gestão pública. No entanto, a análise manual desses relatórios é penosa e requer o conhecimento de especialistas. Nós propomos um framework estatístico para guiar o uso desses dados textuais na construção de indicadores objetivos de corrupção e em modelos de inferência. O framework consiste em duas etapas gerais. Na primeira, usamos métodos de aprendizagem de máquinas para classificação das irregularidades constatadas durante as auditorias. Na segunda etapa, construímos um indicador de corrupção baseado na classificação e o utilizamos em um modelo de regressão, ajustando pelo erro de medida derivado da primeira etapa. Para validar essa metodologia, nós replicamos a estratégia empírica apresentada por Ferraz et al. (2012) para estimar o efeito da corrupção em fundos educacionais nos resultados escolares de alunos do Ensino Fundamental, entre os anos de 2006-2015. Nós obtemos uma acurácia média de 92% na classificação binária de irregularidades, e nossos resultados corroboram com os encontrados em Ferraz et al.: estudantes de escolas municipais apresentam resultados significativamente piores em testes padronizados se estudam municípios com indícios de corrupção na área de educação

This dissertation provides three novel methodologies to the field of political science. In the first chapter, I describe how to make causal inferences in the face of dynamic strategies. Traditional causal inference methods assume that these dynamic decisions are made all at once, an assumption that forces a choice between omitted variable bias and post-treatment bias. I resolve this dilemma by adapting methods from biostatistics and use these methods to estimate the effectiveness of an inherently dynamic process: a candidate's decision to "go negative." Drawing on U.S. statewide elections (2000-2006), I find, in contrast to the previous literature, that negative advertising is an effective strategy for non-incumbents. In the second chapter, I develop a method for handling measurement error. Social scientists devote considerable effort to mitigating measurement error during data collection but then ignore the issue during analysis. Although many statistical methods have been proposed for reducing measurement error-induced biases, few have been widely used because implausible assumptions, high levels of model dependence, difficult computation, or inapplicability with multiple mismeasured variables. This chapter develops an easy-to-use alternative without these problems as a special case of extreme measurement error and corrects for both. In the final chapter, I introduce a model for detecting changepoints in the distribution of contributions data because it allows for overdispersion, a key feature of contributions data. While many extant changepoint models force researchers to choose the number of changepoint ex ante, the game-changers model incorporates a Dirichlet process prior in order to estimate the number of changepoints along with their location. I demonstrate the usefulness of the model in data from the 2012 Republican primary and the 2008 U.S. Senate elections. / Government

No description available.