This study was conducted to evaluate the ability of AN-DRG version 3.1 to predict variation in patients' lengthof stay in hospital (LOS) and identify other factors that can influence the LOS by using routinely collectedhospital morbidity data. A total of 18 DRGs that comprised 4,589 episodes were analysed. Multiple regressionwas used to model length of stay as a function of a number of independent variables. Overall only 37.6% ofvariation in mean length of stay could be explained. DRGs predicted 30% of the total variation. Other factorssuch as age, payment classification, source of referral, specialty of doctor, and ethnic group also influencedpatient length of stay. It was concluded that the limited explanation was a consequence of a lack of a betterindicator of severity within DRGs.