OBJECTIVES: The purpose of this study was to estimate cancer incidence for American Indians in Minnesota. METHODS: Indian Health Service enrollment data were linked to the Minnesota tumor registry to identify cancers among American Indians in Minnesota. Incidence rates for the 5 most common cancers in this population, estimated after the linkage, were compared with rates estimated before the linkage and with rates for the total population of Minnesota. RESULTS: The linkage identified 302 cancer cases not previously identified as occurring among American Indians in Minnesota. Postlinkage estimates suggested that incidence rates for prostate and colorectal cancer are similar to those for the total population of Minnesota, but that rates of lung and cervical cancer are significantly higher. Breast cancer rates are slightly lower than those for the total population of Minnesota but more than twice as high as previous estimates for American Indians. CONCLUSIONS: The postlinkage estimates suggest different priorities for cancer education, prevention, and control than might be assumed from either prelinkage estimates or previously published data, and underscore the importance of using accurate and specific data for setting these priorities.