When study subjects are obtained through sampling procedures based on the level of known characteristics, covariate data can be used to adjust effect estimates. This principle, which is well-understood for both exposure-based sampling (cohort studies) and disease-based sampling (case-control studies), can also be applied to cross-classifications of the source population. An opportunity for exposure--disease-based sampling arises whenever data on exposure and disease are both available on a group of subjects who are incompletely characterized in terms of other covariates. This is a common intermediate stage in epidemiologic studies of many kinds.