Randomized clinical trials (RCTs) are widely considered to be the gold standard of evidence for treatment efficacy, but they have not been widely applied to rehabilitation or, more specifically, traumatic brain injury rehabilitation. Ethical, scientific, and resource factors may limit the application of RCTs. Thus, rigorous observational alternatives to the RCT would be of great value. In the article by Powell et al, an attempt to rigorously apply an observational design to assess the relative effectiveness of inpatient rehabilitation versus home discharge failed to control for important confounding factors. It appears nearly impossible to successfully apply observational designs when the factors leading to the applications of different treatments are strongly related to the patient's perceived prognosis. However, observational designs may be successfully applied when regional or temporal variations in care are studied. Moreover, a number of developments in measurement, study design, and statistical analysis may expand the role of observational studies in answering questions of rehabilitation efficacy and effectiveness.