Beyond the benefits for reducing selection bias, there is an important political reason to prefer randomized over matched studies at this point in history. Because of political developments in Washington, we have a once-in-a-lifetime opportunity to reverse the “awful reputation” that educational research has among policymakers (Kaestle, 1993; Lagemann, 2002). This is a time when it makes sense to concentrate resources and energies on a set of randomized experiments of impeccable quality and clear policy importance to demonstrate that such studies can be done. Over the longer run, I believe that a mix of randomized and rigorous matched experiments evaluating educational interventions would be healthier than a steady diet of randomized experiments, but right now we need to establish the highest possible standard of evidence, on a par with standards in other fields, to demonstrate what educational research can accomplish.