Term
| randomized, posttest-only, control group design |
|
Definition
| a type of experimental design; random assigns controls for selection; other confounding variables are controlled by comparing the treatment and no treatment groups |
|
|
Term
| randomized, prettest-posttest control group design |
|
Definition
| a type of experimental design; adding a pretest allows us to quantify the amount of change following treatment; also allows us to verify that the groups were equal initially; a strong basic research with excellent control over confounding |
|
|
Term
| multilevel, randomized between-subjects design |
|
Definition
| a type of experimental design; may or may not include a pretest; multi-group extension of the basic experimental designs; controls virtually all sources of confounding variables |
|
|
Term
| solomon's four group design |
|
Definition
| a type of experimental design; combines two basic experimental designs; randomized posttest only control group design and randomized prettest-posttest control group design; allows the assessment of an interaction between the pretest and the treatment; two groups receive treatment and two do not |
|
|
Term
|
Definition
| a type of nonexperimental design; a very weak design; what we do when we try to figure out after the fact what caused somethign to happen; not good science; does not control confounding variables |
|
|
Term
| single-group, posttest only design |
|
Definition
| a type of nonexperimental design; even with the manipulation, virtually no control over confounding variables; we tend to use implicit control group (what we think would have happened if there had been no manipulation) |
|
|
Term
| single-group prettest-posttest deisgn |
|
Definition
| type of nonexperimental design; the pretest documents change, but factors other than treatment could have accounted for the change (history, maturation, regression etc) |
|
|
Term
| prettest-posttest natural control group design |
|
Definition
| type of nonexperimetnal design; like an experiment except that the participants are not randomly assigned to the groups; a reasonably strong design except it does not control for selection which could be a powerful confounding variable |
|
|
Term
|
Definition
| two or more independent variables; all levels of independent variables are combined with all levels of the other independent variable to produce all possible conditions; has great flexibility for exploring or enhancing the "signal" (treatment) in any studies; is efficient' instead of conducting a series of independent studies it effectively combines these studies into one and is effective at examining interaction effects |
|
|
Term
|
Definition
| compares two sets of scores in which the scores are paired as in before and after design |
|
|
Term
|
Definition
| all participants are exposed to all experimental controls; need to control for sequence effects (experience with one condition affecting performance in subsequent conditions); controlled by counterbalance; appropriate statistic |
|
|
