RCT is a type of scientific experiment that features the random assignment of individuals to either a focal treatment group or a control group that does not receive the treatment. Data collection and analysis of the two groups on the same measures are then subjected to periodic data analysis to determine the nature and magnitude of differences between the two groups that are likely due to program participation. The advantage of RCTs compared to other evaluation methods is their ability to establish a reliable causal link between a program or policy and what occurs in the attitudes and behaviors of those under its influence. This is termed causal inference. This article outlines what is needed to develop a strong causal link between a specific program or policy and a measured outcome. Although there are various statistical options for establishing a comparison group, the RCT is concluded to be the strongest design, because it best establishes equally comparable groups on all known/measurable and unknown/unmeasurable factors. This is done by assigning eligible individuals at random to either a treatment group or to a control group. By random assignment, the treatment and control groups are essentially identical on all observed and unobserved factors. This article also explains why a quasi-experimental alternative to the RCT should not be used. It also identifies and discusses common objections to conducting RCTs in corrections, and it cautions that corrections practices labeled as "evidence-based" must be examined to determine whether they were established under a RCT evaluation. A case study of RCT evaluation in a Pennsylvania state prison is provided, along with a brief discussion of RCT evaluations in policing.