From individual-level longitudinal data for two entire cohorts of medical students in UK universities, we analyse the probability that an individual student will ‘drop out’ of medical school prior to the successful completion of their studies. We examine the cohort of students enrolling for a medical degree at the start of the academic years 1985 or 1986. We find evidence that medical student completion is influenced by measures of academic preparedness, sex, and age as well as by the characteristics of the medical school itself. On the basis of our results, we also comment on the construction of institutional performance indicators against the criterion of student dropout.