Le risque attribuable (RA) mesure la proportion de cas de maladie qui peuvent être attribués à une exposition au niveau de la population. Plusieurs définitions et méthodes d'estimation du RA ont été proposées pour des données de survie. En utilisant des simulations, nous comparons quatre méthodes d'estimation du RA dans le contexte de l'analyse de survie : deux méthodes non paramétriques basées sur l'estimateur de Kaplan-Meier, une méthode semi-paramétrique basée sur le modèle de Cox à risques proportionnels et une méthode paramétrique basée sur un modèle à risques proportionnels avec un risque de base constant par morceaux. Nos travaux suggèrent d'utiliser les approches semi-paramétrique et paramétrique pour l'estimation du RA lorsque l'hypothèse des risques proportionnels est vérifiée. Nous appliquons nos méthodes aux données de la cohorte E3N pour estimer la proportion de cas de cancer du sein invasif attribuables à l'utilisation de traitements hormonaux de la ménopause (THM). Nous estimons qu'environ 9 % des cas de cancer du sein sont attribuables à l'utilisation des THM à l'inclusion. Dans le cas d'une exposition protectrice, une alternative au RA est la fraction préventive (FP) qui mesure la proportion de cas de maladie évités. Cette mesure n'a pas été considérée dans le contexte de l'analyse de survie. Nous proposons une définition de la FP dans ce contexte et des méthodes d'estimation en utilisant des approches semi-paramétrique et paramétrique avec une extension permettant de prendre en compte les risques concurrents. L'application aux données de la cohorte des Trois Cités (3C) estime qu'environ 9 % de cas d'accident vasculaire cérébral peuvent être évités chez les personnes âgées par l'utilisation des hypolipémiants. Notre étude montre que la FP peut être utilisée pour évaluer l'impact des médicaments bénéfiques dans les études de cohorte tout en tenant compte des facteurs de confusion potentiels et des risques concurrents. / The attributable risk (AR) measures the proportion of disease cases that can be attributed to an exposure in the population. Several definitions and estimation methods have been proposed for survival data. Using simulations, we compared four methods for estimating AR defined in terms of survival functions: two nonparametric methods based on Kaplan-Meier's estimator, one semiparametric based on Cox's model, and one parametric based on the piecewise constant hazards model. Our results suggest to use the semiparametric or parametric approaches to estimate AR if the proportional hazards assumption appears appropriate. These methods were applied to the E3N women cohort data to estimate the AR of breast cancer due to menopausal hormone therapy (MHT). We showed that about 9% of cases of breast cancer were attributable to MHT use at baseline. In case of a protective exposure, an alternative to the AR is the prevented fraction (PF) which measures the proportion of disease cases that could be avoided in the presence of a protective exposure in the population. The definition and estimation of PF have never been considered for cohort studies in the survival analysis context. We defined the PF in cohort studies with survival data and proposed two estimation methods: a semiparametric method based on Cox’s proportional hazards model and a parametric method based on a piecewise constant hazards model with an extension to competing risks. Using data of the Three-City (3C) cohort study, we found that approximately 9% of cases of stroke could be avoided using lipid-lowering drugs (statins or fibrates) in the elderly population. Our study shows that the PF can be estimated to evaluate the impact of beneficial drugs in observational cohort studies while taking potential confounding factors and competing risks into account.

Survival analytic methods help to analyze lifetime data arising from medical and reliability experiments. The popular proportional hazards model, proposed by Cox (1972), is widely used in survival analysis to study the effect of risk factors on lifetimes. An important assumption in regression type analysis is that all relative risk factors should be included in the model. However, not all relative risk factors are observed due to measurement difficulty, inaccessibility, cost considerations, and so on. These unobservable risk factors can be modelled by the so-called frailty model, originally introduced by Vaupel et al. (1979). Furthermore, the frailty model is also applicable to clustered data. Cluster data possesses the feature that observations within the same cluster share similar conditions and environment, which are sometimes difficult to observe. For example, patients from the same family share similar genetics, and patients treated in the same hospital share the same group of profes- sionals and same environmental conditions. These factors are indeed hard to quantify or measure. In addition, this type of similarity introduces correlation among subjects within clusters. In this thesis, a semi-parametric frailty model is proposed to address aforementioned issues. The baseline hazards function is approximated by a piecewise constant function and the frailty distribution is assumed to be a Birnbaum-Saunders distribution. Due to the advancement in modern medical sciences, many diseases are curable, which in turn leads to the need of incorporating cure proportion in the survival model. The frailty model discussed here is further extended to a mixture cure rate frailty model by integrating the frailty model into the mixture cure rate model proposed originally by Boag (1949) and Berkson and Gage (1952). By linking the covariates to the cure proportion through logistic/logit link function and linking observable covariates and unobservable covariates to the lifetime of the uncured population through the frailty model, we obtain a flexible model to study the effect of risk factors on lifetimes. The mixture cure frailty model can be reduced to a mixture cure model if the effect of frailty term is negligible (i.e., the variance of the frailty distribution is close to 0). On the other hand, it also reduces to the usual frailty model if the cure proportion is 0. Therefore, we can use a likelihood ratio test to test whether the reduced model is adequate to model the given data. We assume the baseline hazard to be that of Weibull distribution since Weibull distribution possesses increasing, constant or decreasing hazard rate, and the frailty distribution to be Birnbaum-Saunders distribution. D ́ıaz-Garc ́ıa and Leiva-Sa ́nchez (2005) proposed a new family of life distributions, called generalized Birnbaum-Saunders distribution, including Birnbaum-Saunders distribution as a special case. It allows for various degrees of kurtosis and skewness, and also permits unimodality as well as bimodality. Therefore, integration of a generalized Birnbaum-Saunders distribution as the frailty distribution in the mixture cure frailty model results in a very flexible model. For this general model, parameter estimation is carried out using a marginal likelihood approach. One of the difficulties in the parameter estimation is that the likelihood function is intractable. The current technology in computation enables us to develop a numerical method through Monte Carlo simulation, and in this approach, the likelihood function is approximated by the Monte Carlo method and the maximum likelihood estimates and standard errors of the model parameters are then obtained numerically by maximizing this approximate likelihood function. An EM algorithm is also developed for the Birnbaum-Saunders mixture cure frailty model. The performance of this estimation method is then assessed by simulation studies for each proposed model. Model discriminations is also performed between the Birnbaum-Saunders frailty model and the generalized Birnbaum-Saunders mixture cure frailty model. Some illustrative real life examples are presented to illustrate the models and inferential methods developed here. / Thesis / Doctor of Science (PhD)