We have conducted a cohort study of cancer risks among 140,208 Swedish farmers in order to compare their cancer risks with those of the general male population. Since there were no individual data regarding exposure to agricultural chemicals and acquiring such data was not realistic, we obtained crude and hypothetical estimates for exposure by dividing the data into time periods, year-of-birth cohorts and geographical areas. The cohort was followed-up in the Cancer Environment Register from 1 January 1971 either until death or until 31 December 1987. The relative risk was computed as the ratio of the observed and expected number of cases (SIR = standardized incidence ratio). A total of 15,040 cases were observed vs 18,918 expected, resulting in a statistically significant decreased SIR of 0.80 (95% confidence interval: 0.78-0.81). The SIR was significantly decreased for several cancer sites, and the lowest value was found for tongue, lung, oesophagus, liver and urinary organs, which is in agreement with other studies on cancer risks among farmers. Other major cancer sites with decreased SIRs were the colon, rectum, pancreas and kidney. Lip cancer and multiple myeloma showed statistically significant increased risks. SIRs for stomach cancer, prostate cancer, skin carcinoma, malignant melanoma, tumours in connective tissue or muscle, malignant lymphomas and leukaemia were all close to unity, which is not consistent with several other studies that have shown increased risks for these sites. For malignant lymphomas the SIR increased over time, though not significantly, and was highest among younger farmers. The SIR for non-Hodgkin lymphoma was lowest in the northernmost region. This gives some support to the hypothesis that there is an association between non-Hodgkin lymphoma and exposure to pesticides and other agricultural chemicals. It is of note that the SIR for multiple myeloma was significantly increased in those parts of Sweden where the use of pesticides has been less frequent and in lower amounts.