Master of Science / Department of Statistics / James J. Higgins / The time for an event to take place in an individual is called a survival time. Examples include the time that an individual survives after being diagnosed with a terminal illness or the time that an electronic component functions before failing. A popular parametric model for this type of data is the Weibull model, which is a flexible model that allows for the inclusion of covariates of the survival times. If distributional assumptions are not met or cannot be verified, researchers may turn to the semi-parametric Cox proportional hazards model. This model also allows for the inclusion of covariates of survival times but with less restrictive assumptions. This report compares estimates of the slope of the covariate in the proportional hazards model using the parametric Weibull model and the semi-parametric Cox proportional hazards model to estimate the slope. Properties of these models are discussed in Chapter 1. Numerical examples and a comparison of the mean square errors of the estimates of the slope of the covariate for various sample sizes and for uncensored and censored data are discussed in Chapter 2. When the shape parameter is known, the Weibull model far out performs the Cox proportional hazards model, but when the shape parameter is unknown, the Cox proportional hazards model and the Weibull model give comparable results.

Background: The study examined the effects of the determinants of under-five mortality in Malawi. It therefore aimed to estimate the rate or prevalence of under-five mortality in Malawi and to examine differentials in infant and child mortality by socio-economic, demographic, environmental, health-seeking behaviour and nutritional value. Methods: This study involved a secondary data analysis of the 2010 Malawi Demographic and Health Survey (MDHS) data set of children under five years old and women who had given birth in the five years preceding the survey. The Kaplan-Meier survival analysis and multivariate hazard analysis were used to examine the relationship between under-five mortality and socio-economic. demographic, environmental, health-seeking behaviour and nutritional factors. Results: The results show that birth order, mother's education, place of residence. region and exclusive breastfeeding were significantly associated with under-five mortality. The results also show that there was no significant association between under-five mortality and other indicators of socio-economic. demographic. environmental, health-seeking behaviour. The results also show that more deaths of under-fives occurred during infancy than during childhood. Conclusion: The results show that more deaths occurred during the first months after birth than after 12 months of age. This showed that mother's education, birth order, place of residence, region and breastfeeding had a greater influence on the survival of the child. / Thesis (M.Soc.Sc. Population Studies) North-West University, Mafikeng Campus, 2014

In Sweden, all banks must report their regulatory capital in their reports to the market and their models for calculating this capital must be approved by the financial authority, Finansinspektionen. The regulatory capital is the capital that a bank has to hold as a security for credit risk and this capital should serve as a buffer if they would loose unexpected amounts of money in their lending business. Loss-Given-Default (LGD) is one of the main drivers of the regulatory capital and the minimum required capital is highly sensitive to the reported LGD. Workout LGD is based on the discounted future cash flows obtained from defaulted customers. The main issue with workout LGD is the incomplete workouts, which in turn results in two problems for banks when they calculate their workout LGD. A bank either has to wait for the workout period to end, in which some cases take several years, or to exclude or make rough assumptions about those incomplete workouts in their calculations. In this study the idea from Survival analysis (SA) methods has been used to solve these problems. The mostly used SA model, the Cox proportional hazards model (Cox model), has been applied to investigate the effect of covariates on the length of survival for a monetary unit. The considered covariates are Country of booking, Secured/Unsecured, Collateral code, Loan-To-Value, Industry code, Exposure-At- Default and Multi-collateral. The data sample was first split into 80 % training sample and 20 % test sample. The applied Cox model was based on the training sample and then validated with the test sample through interpretation of the Kaplan-Meier survival curves for risk groups created from the prognostic index (PI). The results show that the model correctly rank the expected LGD for new customers but is not always able to distinguish the difference between risk groups. With the results presented in the study, Nordea can get an expected LGD for newly defaulted customers, given the customers’ information on the considered covariates in this study. They can also get a clear picture of what factors that drive a low respectively high LGD. / I Sverige måste alla banker rapportera sitt lagstadgade kapital i deras rapporter till marknaden och modellerna för att beräkna detta kapital måste vara godkända av den finansiella myndigheten, Finansinspektionen. Det lagstadgade kapitalet är det kapital som en bank måste hålla som en säkerhet för kreditrisk och den agerar som en buffert om banken skulle förlora oväntade summor pengar i deras utlåningsverksamhet. Loss- Given-Default (LGD) är en av de främsta faktorerna i det lagstadgade kapitalet och kravet på det minimala kapitalet är mycket känsligt för det rapporterade LGD. Workout LGD är baserat på diskonteringen av framtida kassaflöden från kunder som gått i default. Det huvudsakliga problemet med workout LGD är ofullständiga workouts, vilket i sin tur resulterar i två problem för banker när de ska beräkna workout LGD. Banken måste antingen vänta på att workout-perioden ska ta slut, vilket i vissa fall kan ta upp till flera år, eller så får banken exkludera eller göra grova antaganden om dessa ofullständiga workouts i sina beräkningar. I den här studien har idén från Survival analysis (SA) metoder använts för att lösa dessa problem. Den mest använda SA modellen, Cox proportional hazards model (Cox model), har applicerats för att undersöka effekten av kovariat på livslängden hos en monetär enhet. De undersökta kovariaten var Land, Säkrat/Osäkrat, Kollateral-kod, Loan-To-Value, Industri-kod Exposure-At-Default och Multipla-kollateral. Dataurvalet uppdelades först i 80 % träningsurval och 20 % testurval. Den applicerade Cox modellen baserades på träningsurvalet och validerades på testurvalet genom tolkning av Kaplan-Meier överlevnadskurvor för riskgrupperna skapade från prognosindexet (PI). Med de presenterade resultaten kan Nordea beräkna ett förväntat LGD för nya kunder i default, givet informationen i den här studiens undersökta kovariat. Nordea kan också få en klar bild över vilka faktorer som driver ett lågt respektive högt LGD.

With the growth of Pentecostalism over the last few decades, conservative values and punitive sanctions related to the sexual behavior of adolescents and unmarried youth began to play an important and systematic role in Pentecostal and renewed Protestant churches as well as in charismatic Catholic communities. Simultaneously, religion has become an important and highly present factor in the lives of many adolescents and youth in Brazil. In terms of attempting to attract this age group, these churches and communities, stand out, as they have used their resources to create a space for this segment of the population to participate in a religious environment. Youth groups, dating groups, trade courses, lectures, aid work in poor communities, confirmation and other activities such as retreats and religious trips, have been frequently observed in these churches and charismatic communities. In this dissertation, I examine the associations between religious involvement and sexual initiation in Brazil. More specifically, I investigate (1) whether religious denomination and religiosity are associated with age at premarital first sexual intercourse, (2) whether these associations have changed over the last three decades, (3) how different churches and religious leaders address sexual behavior issues, and (4) the mechanisms through which religion can influence adolescents’ sexual behavior in Brazil. These research questions are assessed by employing multiple data sources and methodologies including three Demographic and Health Surveys carried out in Brazil in 1986, 1996, and 2006 and event history analysis, as well as in-depth interview data and participant observation among different religious groups and affiliations by attending several Catholic masses, Protestant religious services, youth groups, Sunday schools, and religious talks/lectures. Quantitative and qualitative findings of this dissertation show that adolescents and youth from Pentecostal churches and communities seem more likely to delay or abstain from premarital sexual initiation when compared to traditional Catholics. I conclude by suggesting that the dissemination of conservative norms and sanctions as well as the availability of greater space for youth to maintain close relationships with these churches have helped create mechanisms through which religion can directly and indirectly influence the lives and sexual behavior of young people in Brazil. / text

Survival Analysis generally uses the median survival time as a common summary statistic. While the median possesses the desirable characteristic of being unbiased, there are times when it is not the best statistic to describe the data at hand. Royston and Parmar (2011) provide an argument that the restricted mean survival time should be the summary statistic used when the proportional hazards assumption is in doubt. Work in Restricted Means dates back to 1949 when J.O. Irwin developed a calculation for the standard error of the restricted mean using Greenwood’s formula. Since then the development of the restricted mean has been thorough in the literature, but its use in practical analyses is still limited. One area that is not well developed in the literature is the choice of the time point to which the mean is restricted. The aim of this dissertation is to develop a data driven method that allows the user to find a cut-point to use to restrict the mean. Three methods are developed. The first is a simple method that locates the time at which the maximum distance between two curves exists. The second is a method adapted from a Renyi-type test, typically used when proportional hazards assumptions are not met, where the Renyi statistics are plotted and piecewise regression model is fit. The join point of the two pieces is where the meant will be restricted. Third is a method that applies a nonlinear model fit to the hazard estimates at each event time, the model allows for the hazards between the two groups to be different up until a certain time, after which the groups hazards are the same. The time point where the two groups’ hazards become the same is the time to which the mean is restricted. The methods are evaluated using MSE and bias calculations, and bootstrap techniques to estimate the variance.

Master of Arts / Department of Statistics / Paul Nelson / There are two important statistical models for multivariate survival analysis, proportional hazards(PH) models and accelerated failure time(AFT) model. PH analysis is most commonly used multivariate approach for analysing survival time data. For example, in clinical investigations where several (known) quantities or covariates, potentially affect patient prognosis, it is often desirable to investigate one factor effect adjust for the impact of others. This report offered a solution to choose appropriate model in testing covariate effects under different situations. In real life, we are very likely to just have limited sample size and censoring rates(people dropping off), which cause difficulty in statistical analysis. In this report, each dataset is randomly repeated 1000 times from three different distributions (Weibull, Lognormal and Loglogistc) with combination of sample sizes and censoring rates. Then both models are evaluated by hypothesis testing of covariate effect using the simulated data using the derived statistics, power, type I error rate and covergence rate for each situation. We would recommend PH method when sample size is small(n<20) and censoring rate is high(p>0.8). In this case, both PH and AFT analyses may not be suitable for hypothesis testing, but PH analysis is more robust and consistent than AFT analysis. And when sample size is 20 or above and censoring rate is 0.8 or below, AFT analysis will have slight higher convergence rate and power than PH, but not much improvement in Type I error rates when sample size is big(n>50) and censoring rate is low(p<0.3). Considering the privilege of not requiring knowledge of distribution for PH analysis, we concluded that PH analysis is robust in hypothesis testing for covariate effects using data generated from an AFT model.

O Atendimento Pré Hospitalar (APH) é um importante recurso no atendimento à vítimas de trauma. No entanto, há muitas dificuldades para demonstrar o efeito benéfico das intervenções do APH na sobrevivência das vítimas, sobretudo as de suporte avançado à vida (SAV). A proposta deste estudo é caracterizar as vítimas de acidentes trânsito, com Revised Trauma Score (RTS) <11, atendidas pelo SAV municipal e encaminhadas a hospitais terciários em São Paulo, além de identificar as variáveis da fase pré-hospitalar associadas à sobrevivência e avaliar o valor predeterminante dessas variáveis sobre o resultado obtido pelas vítimas. As variáveis avaliadas foram: sexo, idade, mecanismos do acidente, procedimentos de suporte básico e SAV realizados, repercussão fisiológica do trauma na cena do acidente, (considerando o RTS , seus parâmetros e flutuações), o tempo consumido no APH, gravidade do trauma segundo o Injury Severity Score (ISS),a Maximum Abbreviated Injury Scale (MAIS) e número de lesões para cada segmento corporal. Os resultados obtidos por 175 vítimas entre 12 e 65 anos, foram submetidos a "Análise de Sobrevivência de Kaplan Meier" e ao “Modelo de Riscos Proporcionais de Cox". A variável dependente foi o tempo de sobrevivência após o acidente, considerando os intervalos até 6h,12h, 24h, 48h, até 7 dias e até o término da internação. Os homens (86,9%) e a faixa etária de 20 a 29 anos (36,0%) foram as mais freqüentes. Os atropelamentos (45,1%) e o envolvimento de motocicletas e seus ocupantes (30,9%) foram os destaques dentre os mecanismos de trauma. A média do RTS na cena e do ISS, foram respectivamente 8,8 e 19,4.Os segmentos corpóreos mais atingidos foram: cabeça (58,8%), membros inferiores (45,1%) e superfície externa (40%). A média de tempo consumido na fase de APH foi 41min (tempo de cena 20,2min). Ocorreram 36% de óbitos, (metade em até 6 horas). A análise estatística revelou 24 fatores associados à sobrevivência, dentre eles, os procedimentos respiratórios avançados e os circulatórios básicos, as variáveis relativas ao RTS e a gravidade (ISS, MAIS e o número de lesões). No modelo final de Cox, ter sido submetido a procedimentos respiratórios avançados, compressões torácicas, apresentar lesão abdominal e ISS>25, foi associado a maior risco para o óbito até 48h após o trauma. Até 7 dias, a compressão torácica não se manteve no modelo final e a PAS de zero a 75mmHg apresentou associação com a morte após o acidente. Até a alta hospitalar, a ausência de PAS na avaliação inicial permaneceu no modelo. A reposição de volume foi o único fator com valor protetor para o risco de óbito presente em todos os momentos / The prehospital care (PH) is an important resource to trauma victims’ care. Nevertheless, there is great difficulty in demonstrating the PH intervention’s positive effect in victim’s survival, especially when concerning the advanced life support (ALS). The aim of this study is to characterize motor vehicle crash victims with Revised Trauma Score (RTS) <11 cared by municipal ALS and moved to tertiary hospitals in São Paulo in addition to identifying the prehospital variables associated to survival, and to evaluate their values as victim survival outcome determinant. The variables evaluated were: sex, age, trauma mechanism, basic life support and ALS procedures, physiological measures in the accident scene (considering the RTS, its parameters and fluctuations), the time consumed in PH phase, trauma severity by Injury Severity Score (ISS), the Maximum Abbreviated Injury Scale (MAIS) and number of lesions in each body region. The main results obtained by 175 victims between 12 e 65 years of age were submitted to the Kaplan Meier Survival Analysis and to Cox Proportional hazards Regression Analysis. The dependent variable was the survival time after the motor vehicle accident considering the intervals up to 6,12,24 and 48hs , up to 7 days and until the time of hospital discharge. Men (86,9%) and the 20 to 29 aged group (36%) were the most frequent. The pedestrians struck by car (45,1%) and the motorcycles (and their riders) (30,9%)were the highlight in trauma mechanisms. The RTS and the ISS average were 8,8 and 19,4 respectively. The more damaged body regions were head (58,8%), lower limbs (45,1%) and external surface (40%).The prehospital time average was 41 min (scene time 20,2min).Death rate was 36% (half of which up to 6hs).The statistical analysis revealed 24 survival associated factors. The ALS and the circulatory basic procedures, the RTS variables and the trauma severity (ISS,MAIS and number of lesions) were within them. In the final Cox Model were associated to higher risk of death up to 48hs after trauma: the submission to ALS respiratory procedures, chest compressions, the presence of abdominal injuries and ISS>25 .Until the 7th day the chest compression was not sustained in a final model and the systolic blood pressure (SBP) from zero to 75mmHg revealed statistical association with death after trauma. Until hospital discharge the SBP absence in scene evaluation remained in the model. The prehospital intravenous fluid refilling was the only factor of protector value to death risk in all moments

O objetivo deste trabalho foi comparar o desempenho do modelo de riscos proporcionais de Cox convencional, modelo de Cox modificado quando os riscos não são proporcionais e o modelo de análise de sobrevida baseado na teoria de processos de contagem. Para tanto utilizou-se uma coorte de 648 pacientes portadores de câncer de pênis, atendidos no Departamento de Cirurgia Pélvica do Hospital A. C. Camargo, no período de 1953 a 1985. Dessa coorte foram selecionadas três amostras com o objetivo de validar internamente os resultados da análise de sobrevida do banco de dados original. Os resultados do modelo de riscos proporcionais de Cox, no banco de dados original, foram confirmados por uma das amostras desse conjunto de dados. Apenas o estadiamento N foi confirmado como fator prognóstico também nas outras duas amostras. O modelo de riscos proporcionais de Cox e o modelo de análise de sobrevida baseado na teoria de processos de contagem apresentaram resultados semelhantes, na definição dos fatores prognósticos dessa coorte de pacientes com câncer de pênis. O modelo utilizando processos de contagem é mais sofisticado, do ponto de vista matemático. Porém o modelo de Cox está disponível em grande número de pacotes estatísticos e a interpretação de seus coeficientes se faz com maior facilidade. Por isso, talvez, continue a ser a técnica estatística mais utilizada quando o objetivo do estudo é definir fatores prognósticos e grupos de risco. Os fatores prognósticos para a sobrevida de pacientes com câncer de pênis foram os estadiamentos T e N e o grau de diferenciação do tumor. Esses resultados foram ajustados pelo ano de início de tratamento no Hospital A.C. Camargo. Os pacientes com prognóstico favorável foram os que apresentaram tumor pequeno, sem presença de linfonodos clinicamente positivos, e tumor bem diferenciado. / The aim of this study was to compare the performance of the Cox proportional hazards model, the Cox model with time-dependent covariates and the survival model using the counting process theory. These methods were applied in a cohort of 648 patients with penile cancer treated at the Department of Pelvic Surgery, Hospital A.C. Camargo (São Paulo-Brazil), between 1953 and 1985. Three samples were selected from the total database in order to check the internal validity. The prognostic factors selected using the Cox proportional hazards model were the same in one sample. The only prognostic factor selected in all samples was the N stage. The T and N stages, and the grade of differentiation were independent prognostic factors of survival using both the Cox proportional hazards model and the survival,model using the counting process theory. The statistical significance was the same and even the values of estimation of the coefficients were very close. The survival model using the counting process is more sophisticated from the mathematical point of view, but the Cox model is more available in statistical software, and, probably because of this, is more applied in survival analysis than the model using the counting processo Patients with small tumors, clinically negatives nodes and well differentiated tumors showed a favorable prognosis. These results were adjusted by year of the beginning in the study.

This dissertation proposes a suite of novel Bayesian semiparametric estimators for a proportional hazard function associated with the gaptimes, or inter-arrival times, of a counting process in survival analysis. The Cox model is applied and extended in order to identify the subsequent effect of an event on future events in a system with renewal. The estimators may also be applied, without changes, to model the effect of a point treatment on subsequent events, as well as the effect of an event on subsequent events in neighboring subjects. These Bayesian semiparametric estimators are used to analyze the survival and reliability of the New York City electric grid. In particular, the phenomenon of "infant mortality," whereby electrical supply units are prone to immediate recurrence of failure, is flexibly quantified as a period of increased risk. In this setting, the Cox model removes the significant confounding effect of seasonality. Without this correction, infant mortality would be misestimated due to the exogenously increased failure rate during summer months and times of high demand. The structural assumptions of the Bayesian estimators allow the use and interpretation of sparse event data without the rigid constraints of standard parametric models used in reliability studies.

We propose classification models for binary and multicategory data where the predictor is a random function. The functional predictor could be irregularly and sparsely sampled or characterized by high dimension and sharp localized changes. In the former case, we employ Bayesian modeling utilizing flexible spline basis which is widely used for functional regression. In the latter case, we use Bayesian modeling with wavelet basis functions which have nice approximation properties over a large class of functional spaces and can accommodate varieties of functional forms observed in real life applications. We develop an unified hierarchical model which accommodates both the adaptive spline or wavelet based function estimation model as well as the logistic classification model. These two models are coupled together to borrow strengths from each other in this unified hierarchical framework. The use of Gibbs sampling with conjugate priors for posterior inference makes the method computationally feasible. We compare the performance of the proposed models with the naive models as well as existing alternatives by analyzing simulated as well as real data. We also propose a Bayesian unified hierarchical model based on a proportional hazards model and generalized linear model for survival analysis with irregular longitudinal covariates. This relatively simple joint model has two advantages. One is that using spline basis simplifies the parameterizations while a flexible non-linear pattern of the function is captured. The other is that joint modeling framework allows sharing of the information between the regression of functional predictors and proportional hazards modeling of survival data to improve the efficiency of estimation. The novel method can be used not only for one functional predictor case, but also for multiple functional predictors case. Our methods are applied to analyze real data sets and compared with a parameterized regression method.