Ascertainment bias in rate ratio estimation from case-sibling control studies of variable age-at-onset diseases

Motivated by a Finnish case-control study of early onset diabetes in which diabetic children are matched to sibling controls, we investigate ascertain ment bias of the usual rate ratio estimator from case-control data under si mplex complete ascertainment of families during a fixed interval of time. A nalytic results indicate that the assumptions necessary for valid estimatio n are that the disease is rare and the factors under study are exchangeable -essentially that the covariate distribution does not depend on calendar ti me or birth order. Further, we found that the rare disease assumption could be dropped by restricting to cases that were diagnosed during the enrollme nt period of the study or including all cases but eliminating the proband a s a control for non-enrollment-period cases. An important consequence of th is work is that standard family-based case-control studies are subject to a scertainment bias if exchangeability of the covariates under investigation does not hold.