O X O
Pre-experimental Designs
On the surface, the design below appears to be an adequate design. The subjects are pretested, exposed a treatment, and then posttested. It would seem that any differences between the pretest measures and posttest measures would be due to the progam treatment.
However, there are serious weaknesses in this design. With the exceptions of selection and morality threat to internal validity, which are not factors due to the lack of a control group, this design is subject to five other threats to internal validity. If a historical event related to the dependent variable intervenes between the pretest and the posttest, its effects could be confused with those of the independent variable. Maturation changes in the subjects could also produce differences between pretest and posttest scores. If paper-and pencil measures are used on a pretest and a different test measure was used on the posttest, a shift of scores from pretest to posttest could occur resulting in a testing threat. Regardless of the measurement process utilized, instrumentation changes could produce variation in the pretest and posttest scores. Finally, if the subjects were selected because they possessed some extreme characteristic, differences between pretest and posttest scores could be due to regression toward the mean.The One-Group Pretest-Posttest Design Experimental Group: O X O
In all of these cases, variation on the dependent variable produced by one or more of the validity threats could easily be mistaken for variation due to the independent variable. The fact that plausible alternative explanation can not be ruled out makes it very difficult to say with any kind of confidence the treatment given caused the observed effect.
The next pre-experimental design involves comparing one group that experiences the treatment with another group that does not.
In considering this design, it is important to recognize that the comparison group that appears to be a control group is not, in the true sense, a control group. The major validity threat to this design is selection. Note that no random assignment (omission of the letter "R") is the indicator that the comparison group nonequivalent. In the above design, the group compared is picked up only for the purpose of comparison. There is no assurance of comparability between it and the experimental group. For example, we might wish to test the impact of a new type of math test by comparing a school in which the program exists with one that does not have the program. Any conclusions we might reach about the effects of the program might be inaccurate because of other differences between the two schools.Experimental group: X O Control group: O
Despite their weaknesses, pre-experimental designs are used when resources do not permit the development of true experimental designs. The conclusions reached from this type of design should be regarded with the utmost caution and the results viewed as suggestive at best (Dooley, 1990).