1003 patients with symptomatic knee osteoarthritis were randomized to be administered either celecoxib 50mg twice daily (b.i.d.), celecoxib 100mg b.i.d., celecoxib 200mg b.i.d., naproxen b.i.d., or placebo. Patients were assessed for efficacy and safety measures over 12 weeks of treatment. Reduction in Western Ontario and McMaster Universities Osteoarthritis Index total scores and OA Severity Index scores after 12 weeks significantly favoured all active treatment groups compared to the placebo group, while pain scores on a visual analog scale were only significantly reduced after 12 weeks compared to placebo in the celecoxib 100mg b.i.d., celecoxib 200mg b.i.d., and the naproxen groups.