A bivariate cure-mixture approach for modeling familial association in diseases

For modeling correlation in familial diseases with variable ages at onset, we propose a bivariate model that incorporates two types of pairwise associ ation, one between the lifetime risk or the overall susceptibility of two i ndividuals and one between the ages at onset between two susceptible indivi duals. For estimation, we consider a two-stage estimation procedure similar to that of Shih (1998, Biometrics 54, 1115-1128). We evaluate the properti es of the estimators through simulations and compare the performance with t hat from a bivariate survival model that allows correlation between ages at onset only. We apply the methodology to breast cancer using the kinship da ta from the Washington Ashkenazi Study. We also discuss potential applicati ons of the proposed method in the area of cure modeling.