Physicians and patients must choose between several therapeutic interventions for rheumatoid arthritis and need to compare the available therapeutic options. Although randomized, placebo-controlled trials are essential to establish the efficacy of a new treatment, they are not much help when it comes to selecting the best therapy for an individual patient. Comparative effectiveness research (CER) is set to provide direct comparisons between therapeutic strategies. CER attempts to weigh the benefits against the potential harms of a particular intervention. Furthermore, CER may help identify specific patient subgroups that are more likely to benefit from a particular therapy or at increased risk of adverse events. Several study designs are available for CER, including pragmatic trials, indirect comparisons using meta-analysis, and observational studies. Understanding the strengths and weaknesses of each design improves the interpretation of the results. In this article, I illustrate CER principles using examples from the literature on biologic antirheumatic agents.