ABSTRACT
This chapter focuses on methods applied to questions of causality such as experiments and quasi-experiments, methods to address questions about group differences, and methods used to answer questions about the direction and strength of relationships among variables. Well-designed experiments have sufficient controls to eliminate alternative explanations, allowing to draw causal conclusions. Quasi-experiments include a comparison of at least two levels of an independent variable, but the manipulation is not always under the experimenter’s control. In differential research, pre-existing groups are cornpared on one or more dependent measures. The ideal control group in differential research is identical to the experimental group on everything except the variable that defines the groups. In interrupted time-series designs, a single group of subjects is measured several times both before and after some event or manipulation. Single-subject designs were developed early in the history of experimental psychology and were used in both human and animal learning studies.
