Quantitative risk assessments for carcinogens conducted by the U.S. EPA have most frequently been based on results of a bioassay from a single sex/strain/species of animal. In some cases, more than one data set derived from different sexes, strains, or species of animals is suitable for quantitative risk assessment. When there is no apparent difference among the data sets in sensitivity to the carcinogen, use of more of the available data should result in a higher level of confidence in the risk estimate. Several biological factors must be considered before combining data from different animal sexes, strains, species, or tumor sites. The relevance of the animal models, study design and execution, dose selection, and route of administration are factors which influence whether data from separate studies should be combined. The decision to combine data sets is also based on what is known of the mechanism of action of the agent, its pharmacokinetics, any species/sex specificity of the effect, and considerations regarding tumor site specificity. Statistical analysis also indicates whether the data sets may be described by the same multistage model. The evaluation of these factors in the decision to combine or not combine data sets is discussed.