Objectives: There are conflicting data on cancer incidence and mortality in psychiatric patients, although most studies suggest that while cancer mortality is higher, incidence is no different from that in the general population. Different methodologies and outcomes may account for some of the conflicting results. We investigated the association between mental illness and cancer incidence, first admission rates, and mortality in Nova Scotia using a standard methodology. Method: A population-based record-linkage study of 247 344 patients in contact with primary care or specialist mental health services during 1995 to 2001 was used. Records were linked with cancer registrations and death records. Results: Cancer mortality was 72% higher in males (95%CI, 63% to 82%) and 59% higher in females (95%CI, 49% to 69%) among patients in contact with mental health services. This was reflected in similarly elevated first admission rates. However, there was weaker and less consistent evidence for increased incidence. For several cancer sites, incidence rate ratios were lower than might be expected given the mortality and first admission rate ratios, and no higher than that of the general population. These were melanoma, prostate, bladder, and colorectal cancers in males. Conclusion: People with mental illness in Nova Scotia have increased mortality from cancer, which cannot always be explained by increased incidence. Possible explanations for further study include delays in detection or initial presentation leading to more advanced staging at diagnosis, and difficulties in communication or access to health care.