Observational epidemiology provides powerful methods for studying the etiology and natural history of renal disease in populations. Existing data sets can be used in the conduct of cross-sectional, case-control, and cohort studies that complement experimental investigations. Analysis of existing data sets is extremely efficient and, in many instances, provides results of similar quality to those derived from studies that depend on the collection of original data. A study based on linkage of hypertensive end-stage renal disease (ESRD) incidence rates from the Maryland Regional ESRD Registry with corresponding prevalence data from a state-wide survey of cardiovascular risk factors (The Maryland Statewide Household Hypertension Survey) illustrates the power, efficiency, and flexibility of observational epidemiologic methods in investigating racial differences in hypertensive ESRD. Such analyses can both test previously established hypotheses and generate new hypotheses for subsequent investigation.