ABSTRACT
This chapter explains the randomized field experiment (RFE) as the gold standard of program evaluation. In the United States, randomized field experiments have been used since the early 1960s. Financial support for national, large-scale randomized field experiments waned after the 1960s, but the use of smaller experimental designs to evaluate programs increased in the 1970s and increased even more in the 1980s and 1990s and continues today. It is rare that the control group gets no treatment at all. Even in medical experiments, the control group gets a placebo, while the experimental group gets the new drug whose efficacy is tested. It is notable that most RFEs focus on poor people in developing countries; poor people in the United States who are dependent on publicly provided, means-tested social services; people in prison; and enlistees in the military. It is also important to stress that the unit of analysis is defined by what is randomly assigned.
