To follow-up patients prescribed paliperidone palmitate long-acting injection (PP) over 1 year to determine factors predicting continuation with PP treatment. Naturalistic observation of patients registered as starting PP in a single healthcare unit in London, UK. Monovariate and multivariate (Cox regression) analysis of factors predicting continuation at 1 year. Data were available for 210 patients consecutively prescribed PP of whom 10 were lost to follow-up. At 1 year, 65% of 200 patients (176 with a diagnosis of schizophrenia or schizoaffective disorder) started on PP were still receiving it. The main reason for discontinuation was perceived ineffectiveness (52% of discontinuers); only 10 subjects (5% of total) discontinued because of adverse effects. Initiation as an out-patient [hazard ratio (HR) 0.39, 95%CI, 0.20, 0.67, P = 0.001]; being switched from risperidone (HR 0.56, 95%CI 0.32, 0.94, P = 0.026) and correct initiation (HR 0.56, 95%CI 0.34, 0.93, P = 0.024) were significantly associated with a lower likelihood of discontinuation. Paliperidone palmitate was effective and well tolerated in this naturalistic cohort. Optimising treatment by targeting PP for patients identified as having lower risk of discontinuation can give rise to continuation rates approaching 80% at 1 year.