Os modelos beta mistos são amplamente utilizados na análise de dados que apresentam uma estrutura hierárquica e que assumem valores em um intervalo restrito conhecido. Com o objetivo de propor um método de predição dos componentes aleatórios destes, os resultados previamente obtidos na literatura para o preditor de Bayes empírico foram estendidos aos modelos de regressão beta com intercepto aleatório normalmente distribuído. O denominado melhor preditor empírico (MPE) proposto tem aplicação em duas situações diferentes: quando se deseja fazer predição sobre os efeitos individuais de novos elementos de grupos que já fizeram parte da base de ajuste e quando os grupos não pertenceram à tal base. Estudos de simulação foram delineados e seus resultados indicaram que o desempenho do MPE foi eficiente e satisfatório em diversos cenários. Ao utilizar-se da proposta na análise de dois bancos de dados da área da saúde, observou-se os mesmos resultados obtidos nas simulações nos dois casos abordados. Tanto nas simulações, quanto nas análises de dados reais, foram observados bons desempenhos. Assim, a metodologia proposta se mostrou promissora para o uso em modelos beta mistos, nos quais se deseja fazer predições. / The mixed beta regression models are extensively used to analyse data with hierarquical structure and that take values in a restricted and known interval. In order to propose a prediction method for their random components, the results previously obtained in the literature for the empirical Bayes predictor were extended to beta regression models with random intercept normally distributed. The proposed predictor, called empirical best predictor (EBP), can be applied in two situations: when the interest is predict individuals effects for new elements of groups that were already analysed by the fitted model and, also, for elements of new groups. Simulation studies were designed and their results indicated that the performance of EBP was efficient and satisfatory in most of scenarios. Using the propose to analyse two health databases, the same results of simulations were observed in both two cases of application, and good performances were observed. So, the proposed method is promissing for the use in predictions for mixed beta regression models.

Os diversos fenômenos solares mostram que a sua atividade não é constante, sendo as manchas solares observadas em sua fotosfera um indicador de atividade do Sol. Os números dessas manchas seguem um ciclo de 11 anos que alterna entre máximos e mínimos; quanto maior o número de manchas, maior o número de erupções no Sol. A literatura médica vem mostrando algumas evidências de que a atividade solar possui alguma relação com a predisposição das pessoas a algumas doenças. As tempestades geomagnéticas são associadas a doenças cardiovasculares, mudanças na pressão arterial sistólica, gravidade da crise de enxaqueca, distúrbios psiquiátricos. As condições da atividade geomagnética são classificadas segundo Batista (2003) em uma escala de Calma, Transição, Ativo, Tempestade fraca, Tempestade intensa ou Tempestade muito intensa. No presente projeto de pesquisa, objetiva-se investigar a associação entre atividade geomagnética e internações diárias por infarto nos hospitais de Ribeirão Preto e região, no período de 1998 a 2007. A hipótese em estudo é que em dias de condições de atividade geomagnética muito perturbada, o número médio de internações por doenças isquêmicas do coração é maior. Para a análise dos dados foi utilizado o modelo de regressão de Poisson com função logarítmica com o auxílio do software SAS 9.2, utilizando o procedimento PROC GENMOD. Observa-se que há evidências de associação entre tempestades geomagnéticas e internações por IAM. / Numerous solar phenomena demonstrate that their activities are not continual, and sunspots noticed in their photosphere are considered an indicator by Suns activity. Numbers linked with these sunspots follow an eleven-year cycle, which alternates between high and low, it means, the greater the number of sunspots, the greater the number of Sun eruptions. Medical Literature has produced evidences that solar activity has some association with people predisposing to some diseases. Geomagnetic storms are related with cardiovascular disease, changes in systolic blood pressure, severity and psychiatric disorders. According to Batista (2003), geomagnetic activity conditions are categorized on a scale of Quiet, Transition, Acting, Weak Storm, Intense Storm or Very Intense Storm. This study intends to investigate the association between geomagnetic activity and daily hospitalization by acute myocardial infarction (AMI) in Ribeirão Preto and its region from 1998 to 2007. The hypothesis being studied is that: day which has unquiet geomagnetic condition, the average number of hospitalizations originated by ischemic heart disease is higher. In order to get on with data analysis, it was used Poissons regression model, with logarithmic function through SAS 9.2, using PROC GENMOD procedure. In consequence, it is observed that there are evidences between geomagnetic storms and hospitalizations by AMI.

Neste trabalho propomos um modelo de regress~ao utilizando a distribuição Weibull modificado, esta distribuição pode ser usada para modelar dados de sobrevivência quando a de função de risco tem forma de U ou banheira. Assumindo dados censurados, é considerado os estimadores de máxima verossimilhança e Jackknife para os parâmetros do modelo proposto. Foram derivadas as matrizes apropriadas para avaliar influiência local sobre os parâmetros estimados considerando diferentes peturbações e também é apresen- tada alguma medidas de influência global. Para diferentes parâmetros fixados, tamanhos de amostra e porcentagem de censuras, varia simulações foram feitas para avaliar a distribuição empírica do resíduo deviance modificado e comparado coma distribuição normal padrão. Esses estudos sugerem que a distribuição empírica do resíduo devianve modificado para o modelo de regressão log-Weibull modificado com dados censurados aproxima-se de uma dis- tribuição normal padrão. Finalmente analisamos um conjunto de dados utilizando o modelo de regressão log-Weibull modificado. Uma nova distribuição de quatro parâmetros é definida para modelar dados de tempo de vida. Algumas propriedades da distribuição é discutida, assim como ilustramos com exemplos a aplicação dessa nova distribuição. Palavras-chaves: Modelo de regressão; Distribuição Weibull modificada; Distribuição weibull modificada generalizada; Análise de sensibilidade; Dados censurados; Análise de resíduo / In this paperwork are proposed a regression model considering the modified Weibull distribution. This distribution can be used to model bathtub-shaped failure rate functions. Assuming censored data, we consider a classic and Jackknife estimator for the parameters of the model. We derive the appropriate matrices for assessing local influence on the parameter estimates under diferent perturbation schemes and we also present some ways to perform global influence. Besides, for diferent parameter settings, sample sizes and censoring percentages, various simulations are performed and the empirical distribution of the deviance modified residual is displayed and compared with the standard normal distribution. These studies suggest that the residual analysis usually performed in normal linear regression models can be straightforwardly extend for a martingale-type residual in log-modifiedWeibull regression models with censored data. Finally, we analyze a real data set under log-modified Weibull regression models. A diagnostic analysis and a model checking based on the deviance modified residual are performed to select an appropriate model. A new four-parameter distribution is introduced. Various properties the new distribution are discussed. Illustrative examples based on real data are also given.

The primary objective of this study is to evaluate the operational effects of U-turn movement at signalized intersections. More specifically, the research objectives include the following parts: To identify the factors affecting the operational performance of U-turning vehicles. In this case, we are particularly interested in the U-turn speeds of U-turning vehicles. To evaluate the impacts of U-turns on capacity of signalized intersections, and To simulate U-turn movement at signalized intersections using Synchro and validate the simulation results. To achieve the research objectives, extensive field data collection work was conducted at sixteen selected sites at Tampa Bay area of Florida. The data collected in the field include: U-turning speed Left turning speed Turning radius Queue discharge time Control delay Hourly traffic volume, and Percentage of U- turning vehicles in left turn lane. Based on the collected field data, a linear regression model was developed to identify the factors affecting the turning speeds of U-turning vehicles at signalized intersections. The model shows the turning speed is significantly impacted by the turning radius and the speed of U-turning vehicles increases with the increase of turning radius. On the basis of field data field data collection, a regression model was developed to estimate the relationship between the average queue discharge time for each turning vehicle and the various percentages of U-turning vehicles in the left turn traffic stream. Adjustment factors for various percentages of U-turning vehicles were also developed by using the regression model. The adjustment factors developed in this study can be directly used to estimate the capacity reduction due to the presence of various percentages of U-turning vehicles at a signalized intersection. The developed adjustment factors were used to improve the simulation of U-turn movement at signalized intersection by using Synchro. The simulation model was calibrated and validated by field data. It was found that using the developed adjustment factors will greatly improve the accuracy of the simulation results for U-turn movement.

Despite an improved understanding of the disease, the prevalence of asthma and asthma-related morbidity continue to rise, particularly among minority and inner-city populations. Despite the growing epidemic of asthma, the surveillance of disease at the state or even local levels is very limited. Such information is very important to identify high-risk population groups and to design more effective community-based preventive interventions or risk management programs that may modify these trends. The study provided important information about spatial differences by the geographical area of residence and changes in asthma hospital admissions over time in the selected area. Environmental exposure to ambient air pollution by ambient particles, sulfur dioxide and ozone was a significant factor to explain the increase in asthma hospitalizations in simple regression analysis, but was not significant after the adjustment to area socioeconomic status characteristics. Sulfur dioxide was the only significant independent variable in a multiple adjusted regression model of hospitalizations for childhood asthma, however, more detailed environmental exposure assessment by calendar quarter suggested that ambient air pollution by sulfur dioxide is not significant variable in the multiple regression model. Future asthma prevention interventions and risk management programs should address population groups described by such socioeconomic status characteristics as poverty, unskilled workers, single parent families with children, families having no vehicle available, people living in less crowded households or socially excluded conditions without adequate family members or relatives support, and also people residing in houses heated by fuel. Developed complex area socioeconomic deprivation index was shown to be a significant predictor of hospital admissions for childhood and adult asthma by zip code area of residence. Predictive loglinear regression model for asthma hospitalizations was further validated by using standard statistical model validation techniques to estimate the accuracy of prediction with new independent dataset outside of our study area. Increase in complex area socioeconomic deprivation index by 1 extra unit could explain the increase by 7.9% in childhood and 7.5% in adult asthma hospitalization in 1997, 8.3% in childhood and 7.2% in adult asthma hospitalizations in 1998, and 7.7% in childhood and 6.7% in adult asthma hospitalizations in 1999 respectively. Predictive log-linear regression model could be successfully applied to develop more effective asthma prevention interventions and risk management programs and to address more sensitive population groups within specific high risk geographical areas.

在子製程相關下所產生的品質特性資料使Shewhart管制圖無法對各別的製程狀態加以解釋，而選控圖可診斷前後製程的責任歸屬。本文提出有n個子製程時，建立選控圖的方法及在製程上之應用，以追蹤製程變異之發生，明確地劃分出子製程的責任歸屬。文中並以模擬資料和實際例證說明，在相關品質特性的資料中，選控圖的建立及診斷效果。在實務上，若產品是由許多相關的子製程共同製造而成時，對於受到前製程影響的品質特性，即可用選控圖進行管制，以獲得正確的製程狀態訊息，並進一步採取正確的管制行動。

This paper is a study on how U.S stock market reacts on sovereign credit rating announcements, and if there is a significant difference between low or high debt firms. We have used an event study based on historical stock prices from 30 companies, 15 with high debt and 15 with low debt. All companies are taken from the S&P`s 500 index which we also use as a market index. We use a regression model with 10 % significance level to see if there is a significant impact on high debt firms. Our result shows that the market will be affected by the downgrade. We also conclude that there was a significant negative impact on the high debt firms.

There are many reasons for companies to hold real estate, including for operating business, production, sales, and providing services. Previous researches show that corporate real estate (CRE) is an important part of company assets, and it will affect stock returns and risk of company. The main object of this study is to investigate the impact of changes in CRE on stock returns and risk of company in Taiwan. Moreover, this study analyzes how CRE affect toward different industry during each business cycle period. Then, we provide some suggestions to stockholders and managers. The data set from 1992 through 2011 in Taiwan stock market, the relationship between CRE and stock returns and risk are analyzed using two stage least squares regression model. The empirical results show that, on average, higher CRE appears to be associated with higher abnormal return performance and higher total risk. On the other hand, CRE show negative impact on business operation such as lower adjusted return on assets and higher risk of bankruptcy. Furthermore, CRE factor is associated with higher abnormal return performance and higher firm value when company with small asset size, high P/E ratio or newly establish characters. Results also indicate that the impact of CRE on firm¡¦s stock price and risk depend on industries, business cycle period, and firm characters. CRE show negative impact on Textile, Tourism, and Trading and Consumers' Goods Industry. In Food Industry, higher CRE factor is associated with lower system risk and positive impact on business operation.

In this study, we consider high frequency transaction data of NYSE, and apply statistical methods to characterize each trade into two classes, influential and ordinary liquidity trades. First, a median based approach is used to establish a high R-square price-volume model for high frequency data. Next, transactions are classified into four states based on the trade price, trade volume, quotes, and quoted depth. Volume weighted transition probability of the four states are investigated and shown to be distinct for informed trades and ordinary liquidity trades. Furthermore, four market reaction factors are introduced and studied. Logistic regression models of the influential trades are established based on the four factors and odds ratios are used to select the cutoff points.

Epidemiological data with disease characteristic information can be modelled in several ways. One way is taking each disease characteristic as a response and constructing binary or polytomous logistic regression model. Second way is using a new response which consists of disease subtypes created by cross-classification of disease characteristic levels, and then constructing polytomous logistic regression model. The former may be disadvantageous since any possible covariation between disease characteristics is neglected, whereas the latter can capture that covariation behaviour. However, cross-classifying the characteristic levels increases the number of categories of response, so that dimensionality problem in parameter space may occur in classical polytomous logistic regression model. A two staged polytomous logistic regression model overcomes that dimensionality problem. In this thesis, study is progressen in two main directions: simulation study and data analysis parts. In simulation study, models that capture the covariation behaviour are compared in terms of the response model parameter estimators. That is, performances of the maximum likelihood estimation (MLE) approach to classical polytomous logistic regression, Bayesian estimation approach to classical polytomous logistic regression and pseudo-conditional likelihood (PCL) estimation approach to two stage polytomous logistic regression are compared in terms of bias and variation of estimators. Results of the simulation study revealed that for small sized sample and small number of disease subtypes, PCL outperforms in terms of bias and variance. For medium scaled size of total disease subtypes situation when sample size is small, PCL performs better than MLE, however when the sample size gets larger MLE has better performance in terms of standard errors of estimates. In addition, sampling variance of PCL estimators of two stage model converges to asymptotic variance faster than the ML estimators of classical polytomous logistic regression model. In data analysis, etiologic heterogeneity in breast cancer subtypes of Turkish female cancer patients is investigated, and the superiority of the two stage polytomous logistic regression model over the classical polytomous logistic model with disease subtypes is represented in terms of the interpretation of parameters and convenience in hypothesis testing.