Campbell & Stanley’s (1963) three general types of experimental designs • Pre-experiments • Quasi-experiments • Full or true experiments
Key concepts • Random assignment: assigning participants to the various conditions in an experiment to achieve equivalent groups for comparison purposes. • Treatment condition: administering the experimental manipulation • Control condition: no experimental manipulation or an alternative, benign manipulation • Pretest: measurement of the dependent variable(s) prior to exposure to a treatment or control condition • Posttest: measurement of the dependent variable(s) following the treatment or control conditions.
notation for experimental designs R = random assignment 01 = pre-test (measurement) 02 = post-test (measurement) X1 = treatment, stimulus condition, or manipulation X0 = control group (no treatment)
PRE-EXPERIMENTAL DESIGNS one-shot case study: A group (usually intact) is administered a treatment and then measured or observed. No attempt is made to randomly assign subjects to condition, nor does the design provide for any additional groups as comparisons. (no random assignment) X1 O1 one group, pre-test, post test design(no random assignment) O1 X O2 static group comparison: only one of two intact groups is given the experimental treatment. At the end of the treatment, both groups are observed or measured to see if there is a difference between them as a result of the treatment. (no random assignment)X1 01 X0 01
Quasi-experimental designs • Pre-test, post-test, quasi-equivalent groups design (no random assignment) 01 X O2 01 O2 • Times-Series design 01 02 03 04
FULL EXPERIMENTAL DESIGNS pre-test/post-test equivalent groups designR 01 X O2 01 O2 post-test only equivalent groups designR T O1 O1 Solomon four-group designR 01 X O2 02 O2 X O2 O2
true/full experimental designs • Solomon Four Group design: attempts to control for the possible "sensitizing" effects of the pre-test or measurement by adding two groups who have not been a part of the pre-test or pre-measurement process. R 01 X1 O2 02 O2 X1 O2 O2
Factorial designs (may be full or quasi-experimental) • Advantage: Allows the researcher to uncover interaction effects • 2 X 2 design • Two independent variables • Two levels/values per variable • Four conditions being compared • 3 X 2 X 2 design • Three independent variables • Three levels/values for one independent variable, two levels/values for the other two independent variables • Twelve conditions being compared