PSYC 3380 Lecture Notes - Lecture 1: Random Assignment, Oa
Document Summary
If participants are randomly assigned, the design is referred to as an experimental design. One variable randomly assigned and one not is still a non-experimental design. Some variables cannot be randomly assigned (ex. personality) Or not ethical (ex. force people to smoke) experimental designs. Very good a determining causality causality and random assignment: counterfactual argument. If the experimenter uses random assignment, the individuals in the control and treatment groups are equivalent at the start of the experiment (theoretically interchangeable) so they represent each other"s counterfactual. Therefore, in the case of random assignment, the effect of the manipulation is simply the difference in y between the treatment and control condition. The change in y can stem from no other cause than that of the manipulation causality and random assignment. The effectiveness of random assignment can depend on sample size. As the sample size decreases, the likelihood of equivalence also decreases.