Ecological studies have suggested that there is an inverse association between the intensity of ambient UV radiation and cancer incidence and mortality. Vitamin D has been posited as a possible driver of these patterns. Observational studies support this hypothesis, having consistently demonstrated an inverse association between circulating 25 hydroxy vitamin D (25(OH)D) concentration and risk of various different types of cancer, particularly colon cancer. Associations with survival and/or mortality have also been shown. However, it is plausible that these findings are due to uncontrolled confounding. Randomised controlled trials (RCTs) can help to determine whether the observed associations are causal, although it is important to note that they can provide information only about the effect of a particular dose of vitamin D, administered to a particular population for a relatively short period of time, often late in the life course. There are few large RCTs that have examined the effect of vitamin D on cancer. These suggest that there is no effect on cancer incidence, and this observation is supported by Mendelian randomisation studies. The RCTs indicate a possible benefit for cancer mortality; Mendelian randomisation studies of cancer-specific mortality are inconsistent. Details of this evidence will be presented, along with a discussion of implications for policy and practice.