Abstract
Randomized controlled trials provide the best evidence for the safety and effectiveness of interventions. However, the reliance on this study design as the only criterion for credible evidence is not possible in all areas of palliative medicine. Although we must exercise caution in making definitive claims from uncontrolled trial data, limitations in performing controlled trials should neither preclude the use of findings from well-designed nonrandomized controlled trials nor, more importantly, deprive patients of potentially effective treatments.