In this study, patients suffering from osteoarthrosis of the hip received two successive periods of treatment, A and B, each of two weeks, with either ketoprofen or a placebo. The daily dosage of ketoprofen was 150 mg in three divided doses of 50 mg. In each case the findings necessary for diagnosis and for assessment of progress during the treatment were recorded. At the end of the trial, the patient's preference for one or other of the two periods of treatment was used as the criterion. The results were analysed by the sequential method. The therapeutic effects assessed by the various criteria included in the protocol (patient's subjective assessment, pain at rest, duration of morning stiffness, distance walked without pain, range of movements, etc.) were also recorded. Nine cases were sufficient to provide a statistically significant result in favour of ketoprofen. In eight cases the preference was definitely in favour of ketoprofen. In a single case there was no preference for one or other of the two periods of treatment (failure of both ketoprofen and placebo). Tolerance to ketoprofen was excellent.