Several studies have suggested that the prevalence of atopic dermatitis has increased over the last three decades, and similar trends have been reported with asthma and hay fever. However, in common with other 'allergic' disease, the definition and measurement of atopic dermatitis in populations has been fraught with problems and has led to difficulties in separating any real changes in disease prevalence from secular changes in diagnosis. In this article, the evidence surrounding the claims of an increased prevalence of atopic dermatitis is examined, and possible reasons for such a change are suggested.