PSYCH 241 Lecture 14: Psych 241 – Lecture 14
Document Summary
Not all experiments provide the same strength of inference. Experiments set up to distinguish between competing theories can produce strong. Ex: early 1900s in southern us: three ds. Much stronger ethics, at least, may mean less control. Quasi-experimental designs often involve collecting data on many variables. Control what you can and/or measure what you can. Use designs and analysis tools to boost experimental sensitivity and maximize statistical power. Select best set of designs and analysis tools to answer qs. A groups similar to the treatment groups serves as a comparison group (as close as possible/practical) Obtain pretest and posttest measures for individuals in both groups (using identical procedures) Random assignment to groups is not used. Pretest scores are used to determine whether the groups are equivalent: can assess equivalence on tested dimension(s) only! Without random assignment to conditions, the two groups are probably not equivalent on many dimensions.