An experiment involves studying two or more groups equivalent in all aspects except that one group is given a treatment and the other groups are not. Any subsequent changes observed in these groups thus can be attributed with a high degree of confidence to the differences in treatment. The use of experimental designs as an appropriate and effective mechanism for developing more informed public policy has been endorsed because the results are seen as giving relatively unambiguous policy direction. Experiments frequently test a range of traditional policies and do not necessarily involve new or innovative practices. The future of field experimentation will be determined by the interest expressed by State and local criminal justice officials and by the contributions of ongoing and future experiments in helping them make policy.