Assessment of estimation procedures for risk and onset hazard with dependent data

Analysis of the role of candidate genes its risk factors for age-dependent hereditary conditions often ignores the importance of dependence among sibs hips or other family clusters for age of onset. We examined the performance of several methods of survival analysis with dependent data using Collabor ative Study on the Genetics of Alcoholism families as submitted for GAW 11. Additionally, an arbitrary truncation of cluster size was performed to exp lore the potential impact of heterogeneity of family size on the resulting inferences concerning the role of candidate genes. Our results showed subst antial differences in attribution of risk to candidate genes according to w hether the method utilized allowed for dependence in onset age and accordin g to whether the sample was truncated or arbitrarily stratified. Further wo rk needs to be done to clarify the importance of properly accounting for de pendent data in age-dependent phenotypes and in integrating these methods i nto widely used genetic analysis computer programs. (C) 1999 Wiley-Liss, In c.