|M.Sc Student||Graber-Naidich Anna|
|Subject||Missing Genetic Information in Case-Control Family Data with|
General Semi-Parametric Shared Frailty Model
|Department||Department of Industrial Engineering and Management||Supervisor||Professor Malka Gorfine-Orgad|
Case-control family studies are now widely used to study the role of gene-environment interactions in the etiology of complex diseases. In these type of studies, exposure levels are obtained retrospectively, and frequently, some of the risk factors, such as genetic information, are observed on the probands but not on their relatives. In this work we consider correlated failure time data arising from population-based case-control family studies with missing genotypes of relatives. A new method for estimating the age-dependence marginalized hazard functions is presented. The main advantages of the proposed technique are:
(1) It is applicable to any frailty distribution with finite moments.
(2) It is based on the pseudo full-likelihood function rather than a pseudo composite likelihood function.
(3) The cumulative baseline hazard function is being estimated sequentially rather than by an iterative process.
We present simulation studies to assess the performance of the proposed methodology. Specifically, we investigated the finite sample properties of our proposed estimators; compared various popular bootstrap methods for the construction of confidence intervals; and evaluated the efficiency loss under the composite-likelihood approach of Chatterjee et al. (2006) and Chen et al. (2009) in compare to our full-likelihood approach. From our simulation results it is evident that the efficiency loss is substantial under a large familial correlation or large number of relatives. Finally, we illustrate the utility of the proposed method on a real data example of breast cancer.