University of Washington - Department of Statistics
Correlated failure time data arise often in many application areas. For example, in genetic epidemiology study, the disease occurrence times of pairs of family members are often correlated and the degree of correlation may provide important leads in respect to disease etiology. Univariate failure time data methods are well established, including Kaplan-Meier method, censored data rank test and Cox regression method. However, the standard tools for multivariate failure data analysis data are not available yet. An efficient nonparametric estimator of the multivariate survivor function having good moderate sample size performance could help stimulate the development of multivariate failure time data methods more generally. Even for bivariate case, the identification of such estimator has proven to be challenging.
In this work, we proposed a new bivariate survivor function estimation method. Also we introduced a new marginal distribution estimation method, which used dependence information between failure times data to improve estimation efficiency.