To examine assumptions underlying federal health statistics on racial and ethnic groups in the United States.Studies conducted by federal agencies and other investigators, and technical appendices of published vital statistics and census reports.Several assumptions underlying federal health statistics on racial and ethnic groups are not well supported. Conceptual (as opposed to operational) definitions of race and ethnicity are not available, and scientific grounds for definition are not considered. Procedures for the ascertainment of race and ethnicity vary within and among data-collection agencies. Miscounting and misclassification may vary by an order of magnitude between whites and other races. The responses of individuals to questions of racial and ethnic identity differ for different indicators, in different surveys, and at different times. As a result, counts, rates, and rate ratios may not be meaningful or accurate. Particularly for Hispanics and for races other than whites or blacks, there are inconsistencies in statistical information that may hinder health research and program development.Improvement of federal health statistics for racial and ethnic groups requires (1) clarification of goals for classification, (2) adoption of scientific principles for the validation and definition of the categories "race" and "ethnicity," (3) assessment of perceived social identity in the population, and (4) periodic evaluation.