Sir,I went through with interest the article entitled “Incidence and factors associated with medication nonadherence in patients with mental illness: A cross-sectional study” published in the “Journal of Postgraduate Medicine” (2015; 16:251-6).[1]The authors have conducted a cross-sectional study in the outpatientpsychiatric department of a tertiary care private hospital over a period of 1 year and followed up the patients receiving at least one psychotropic medication for at least 1 month. The authors concluded that the overall incidence of medication nonadherence in patients with mental illness was 43%. I have concerns regarding the calculation of incidence for which reference to time is important.[2]The authors have actually provided us with an estimate of the proportion of nonadherence among patients on psychotropic medication and not incidence. As incidence involves a reference to time; it is not expressed as a percentage (as done by the authors) but as person-time.[3] In contrast, the proportion in statistics refers to the fraction of the total that possesses a certain attribute such as nonadherence in case of this study.