Hurricanes have been considered one of the most costly disasters in United State, which lead to both economic loss and human fatalities. Therefore, understanding the characteristics of those who evacuated and of those who did not evacuate have been principal focus of some previous researches related to hurricane evacuation behavior. This research presents two sets of decision-making models for analyzing hurricane evacuation behavior, using two statistical methods: standard logistic model and mixed logistic model.The receipt of evacuation order, elevation, expenditure, the presence of children and elderly people, ownership of a house, and receipt of hurricane warning are found to be extremely important in evacuation decision making. When the mixed logistic model is applied, the rate of concern about hurricane threat is assumed to be random according to normal distribution. Mixed logistic models which account for the heterogeneity of household responses are found to perform better than standard logistic model.

This study compares the behavior of differential equations and difference equations of various orders in order to predict the state of the systems at a given time by using initial information about the system. We have demonstrated that differential equations are used in a continuous domain whereas difference equations are employed for discrete dynamical systems. Furthermore, the difference between the two models is amplified in logistic models which both are known to give explicit solutions. However, the discrete logistic model is especially superior in exhibiting a chaotic behavior of the system which the differential equation is incapable of dealing with. The conclusions drawn from the findings conform the similarities and the stark differences between these two models.

The growing empirical literature testing informational efficiency of real estate markets uses data from various contexts and at different levels of aggregation. The results of these studies are mixed. We use a distinctive meta-analysis to examine whether some of these study characteristics and contexts lead to a significantly higher chance for identification of an efficient real estate market. The results generated through meta-regression suggest that use of stock market data and individual level data, rather than aggregate data, significantly improves the probability of a study concluding efficiency. Additionally, the findings neither provide support for the suspicion that the view of market efficiency has significantly changed over the years nor do they indicate a publication bias resulting from such a view. The statistical insignificance of other study characteristics suggests that the outcome concerning efficiency is a context-specific random manifestation for the most part. (authors' abstract)

none

No description available.

INTRODUCTION: Smoking is the leading cause of preventable death in the United States and has been shown to be harmful to human health. Among alternative tobacco products, e-cigarettes have been widely regarded as the safest substitute to the traditional cigarette. However, debate remains about their safety and possible ill effects. AIM: The purpose of this study was to assess characteristics associated with e-cigarette use (everyday/some days/no use) and examine factors related to former smokers replacing a traditional smoking habit with e-cigarette use (yes/no). METHODS: A secondary data analysis was conducted with the Public Use Files (PUFs) for the Population Assessment of Tobacco and Health (PATH) Study, a nationally representative, longitudinal cohort study of tobacco use. Bivariate and multivariable unweighted and weighted generalized linear models were developed for value and comparative purposes, as well as multilevel models to account for within geographical region clustering. Ordinal logistic regression was used to analyze the ordinal e-cigarette use outcome, and logistic regression with the e-cigarette smoking status of former smokers outcome. RESULTS: Covariates associated with e-cigarette use included having rules that allowed smoking non-combustible tobacco inside the home (everyday vs no use: OR = 0.33, CI = 0.27-0.41; somedays vs no use: OR = 0.58, CI = 0.53-0.64), older than 35 years old (everyday vs no use: OR = 0.63, CI = 0.52-0.75; somedays vs no use: OR = 0.86, CI = 0.76-0.96), and positive or neutral self-opinion on tobacco (everyday vs no use: OR = 0.88, CI = 0.73-1.05; somedays vs no use: OR = 1.38, CI = 1.22-1.55). Factors related to e-cigarette use in former smokers included rules allowing non-combustible tobacco products inside the home (Weighted: OR = 0.19, CI = 0.15-0.24; Unweighted: OR = 0.15, CI = 0.12-0.19; Mixed: OR = 0.19, CI = 0.15-0.24), aged 18-35 years (Weighted: OR = 1.45, CI = 1.16-1.80; Unweighted: OR = 2.91, CI = 2.27-3.72; Mixed: OR = 1.45, CI = 1.16-1.80), and not having any health insurance (Weighted: OR = 0.57, CI = 0.44-0.75; Unweighted: OR = 0.47, CI = 0.34-0.64; Mixed: OR = 0.57, CI = 0.44-0.75). DISCUSSION: Family tolerance of smoking and one’s self-opinion on tobacco were factors found to be strongly associated with e-cigarette use. The prevalence of e-cigarette use among young adults raises concerns and necessitates a multi-disciplinary approach to monitor and intervene. Further study is needed to better understand e-cigarette smoking consumption behavior and effects.

<p>  </p> <p>The major concern about vehicle crashes has led to a great amount of research on the topic in the road safety area. Nevertheless, real-world crash data collection periods are often extensive and they result in a great delay in improving safety. Therefore, surrogate measures of safety, such as traffic conflicts, are considered for safety management.</p> <p>The definition of a traffic conflict has evolved over the course of half a century. One of the current definitions encompasses a failure-based road event that inevitably results in a crash if no evasive action is taken by involved road users. This counterfactual concept was validated with specific road events datasets, including rear-end events and vehicle-bicycle encounters. However, observing conflicts for an extended period is still a major difficulty. For example, a LIDAR-based technique applicable to intersections can collect conflict data for a relatively short period of several days. The LiDAR-collected data are then converted to the corresponding expected crash frequency during the observation period, which eventually must be expanded to the corresponding annual value. The conversion step has not been sufficiently addressed in the past research. Thus, an important task of estimating the annual expected crash frequency based on a short-term estimate remains unanswered. Addressing this need is the research objectives and contribution of this study.</p> <p>Advanced statistical methods allow developing models to estimate expected crash frequencies for annual and short periods. The ratio of such two estimates is defined as an expansion factor in this study. This thesis presents the modeling effort and its results for different types of crashes at signalized and unsignalized intersections in Indiana. Traditional and emerging data, such as traffic volume, speed, road characteristics, weather, and other features were collected and assembled at randomly selected 194 intersections. Then, they were used to estimate the logistic models of hourly crash probability. The models were then utilized to calculate expansion factors for a specific intersection.to evaluate the method.</p>

M.Sc. (Statistics)

M.Sc. (Statistics)

A predição de uma observação futura para modelos mistos é um problema que tem sido extensivamente estudado. Este trabalho trata o problema de atribuir valores para os efeitos aleatórios e/ou variável resposta de novos grupos para o modelo logístico misto, cujo objetivo é predizer respostas futuras com base em parâmetros estimados previamente. Na literatura, existem alguns métodos de predição para este modelo que considera apenas o intercepto aleatório. Para a regressão logística mista com k efeitos aleatórios, atualmente não há métodos propostos para a predição dos efeitos aleatórios de novos grupos. Portanto, foram propostas novas abordagens baseadas no método da média zero, no melhor preditor empírico (MPE), na regressão linear e nos modelos de regressão não-paramétricos. Todos os métodos de predição foram avaliados usando os seguintes métodos de estimação: aproximação de Laplace, quadratura adaptativa de Gauss-Hermite e quase-verossimilhança penalizada. Os métodos de estimação e predição foram analisados por meio de estudos de simulação, com base em sete cenários, com comparações de diferentes valores para: o tamanho de grupo, os desvios-padrão dos efeitos aleatórios, a correlação entre os efeitos aleatórios, e o efeito fixo. Os métodos de predição foram aplicados em dois conjuntos de dados reais. Em ambos os problemas os conjuntos de dados apresentaram estrutura hierárquica, cujo objetivo foi predizer a resposta para novos grupos. Os resultados indicaram que o método MPE apresentou o melhor desempenho em termos de predição, entretanto, apresentou alto custo computacional para grandes bancos de dados. As demais metodologias apresentaram níveis de predição semelhantes ao MPE, e reduziram drasticamente o esforço computacional. / The prediction of a future observation in a mixed regression is a problem that has been extensively studied. This work treat the problem of assigning the random effects and/or the outcome of new groups for the mixed logistic regression, in which the aim is to predict future outcomes based on the parameters previously estimated. In the literature, there are some prediction methods for this model that considers only the random intercept. For the mixed logistic regression with k random effects, there is currently no method for predicting the random effects of new groups. Therefore, we proposed new approaches based on average zero method, empirical best predictor (EBP), linear regression and nonparametric regression models. All prediction methods were evaluated by using the estimation methods: Laplace approximation, adaptive Gauss-Hermite quadrature and penalized quasi-likelihood. The estimation and prediction methods were analyzed by simulation studies, based on seven simulation scenarios, which considered comparisons of different values for: the group size, the standard deviations of the random effects, the correlation between the random effects, and the fixed effect. The prediction methods were applied in two real data sets. In both problems the data set presented hierarchical structure, and the objective was to predict the outcome for new groups. The results indicated that EBP presented the best performance in prediction terms, however it has been presented high computational cost for big data sets. The other methodologies presented similar level of prediction in relation to EBP, and drastically reduced the computational effort.