Experiments Versus Quasi-experiments

Abstract

Donald Campbell privately distributed a paper in 1953 entitled “Designs for Social Science Experiments. ” It became the basis for a subsequent article (D.T. Campbell, 1957) in which the distinction between internal and external validity was first introduced to the psychological literature. That article was especially noteworthy for presenting in detail the formal logic whereby random assignment to conditions (e.g., treatment vs. control) made implausible some specific classes of threats to internal validity. Later this aspect of assignment arrangements, randomization, was used to distinguish “true experiments” from “quasi-experiments” (D.T. Campbell & Stanley, 1963). Indeed, the special relationship of randomization to internal validity was given such prominence that the term experiment was taken to mean a randomized experiment unless otherwise noted—a convention we follow in this chapter.