A multivariate hierarchical analysis was used to assess the significance of several demographic and clinical factors in multiple sclerosis patients. We used the time to reach level 6 on the disability status scale (DSS) of Kurtzke as endpoint. Several factors at presentation were significantly associated with an adverse outcome including older age at onset, male sex, cerebellar involvement or insidious onset of a motor deficit as first symptom. Factors ascertained later which were associated significantly with a worse outcome, even after controlling for those previously mentioned, included persisting deficits in brainstem, cerebellar or cerebral systems, a higher frequency of attacks in the first 2 yrs after onset of disease, a short first interattack interval and higher DSS at 2 yrs and 5 yrs from onset. An analysis similar to multiple regression was used to generate predictive models which permit the calculation of the median time to DSS 6 for patients with a given set of covariates. The goodness of fit of these models to the data and their predictive accuracy are discussed.