There is biologic and histogenetic plausibility for an association between salivary gland cancer and nonmelanoma skin cancer. To add further credence to this association, a descriptive epidemiologic study of salivary gland cancer incidence data from the Surveillance Epidemiology and End Results (SEER) program from 1973 to 1981 was undertaken. The objective was to determine whether the incidence of this cancer exhibited the inverse association with geographic latitude that is characteristic of skin cancer incidence. The SEER areas were grouped into three regions (north, central, and south), based on indices of ultraviolet radiation. The southern area had significantly higher rates for white males and females compared with the northern area for all histologic subtypes combined (standardized incidence ratios were 1.6 for males and 1.4 for females), as well as for specific histologic subtypes (adenocarcinoma, squamous cell carcinoma, and males only with mucoepidermoid carcinoma). However, there were no significant differences in incidence between the central and northern areas. These data provide further evidence of an association between skin and salivary neoplasms, both exhibiting a pattern of incidence suggestive of susceptibility to ultraviolet radiation exposure.