It defines terms and contrasts experimentation with other possible research methods. It describes major criminological experiments in three areas: programs to help offenders and potential offenders in their natural environment, police courts and penal institutions, and committing and reporting crimes. The essay also reviews major methodological, practical, and ethical problems arising in randomized experiments, and discusses when these experiments are feasible. It notes that despite their methodological advantages, few randomized experiments have been carried out on crime and justice topics. Most have investigated the effects of providing special help to offenders and, in most cases, this help proved no more effective in reducing reoffending treatment than did existing alternative treatment methods. It is difficult to arrange randomized experiments because program administrators are willing to relinquish control of assignments to experimenters and because of ethical problems involving denial of treatment. The essay emphasizes methodological issues rather than substantive results. Only experiments published in English are included. In most cases, these have been carried out in North America, Great Britain, Australia, New Zealand, the Netherlands, and the Scandinavian countries. About 140 reference, footnotes, and tables are included. (Author abstract modified)