|M.Sc Student||Nadia Bordo|
|Subject||A Nonparametric Estimator of the Survival Function Based|
on Case-Control Family Data
|Department||Department of Industrial Engineering and Management||Supervisor||Professor Gorfine-Orgad Malka|
|Full Thesis text|
Consider data which arise from a typical case-control family study, where individuals with a disease under study (case-probands) and individuals who do not have the disease (control-probands) are randomly sampled from well defined populations. In addition, age at onset or age at censoring and disease status are also observed for one relative of each proband. For example, case-probands are women diagnosed with breast cancer, control-probands are breast cancer free women, and information is collected also on their sisters. Genetic and environmental background that the family members share leads to correlation among the outcomes within a family.
We provide a novel nonparametric estimator of the marginal survival function based on kernel estimators of the conditional survival functions under intracluster dependence. We present extensive simulation study to assess the finite sample properties of the proposed methodology, and show that our proposed estimators perform very well in terms of bias. To illustrate the utility of our proposed procedure, we analyze a case-control family study of early onset prostate cancer.