Evidence-Based Practice for Nurses

rigidly defined protocol for implementation; and (6) all
subjects in both groups are measured on the dependent
variable (DV) using the same method of measurement at
the same points in time.

There are six types of true experimental designs com-
monly reported in the scientific literature. These include: (1) two-group pretest-
posttest, (2) two-group posttest-only, (3) Solomon four-group, (4) multiple
experimental groups, (5) factorial, and (6) crossover designs.

Two-Group Pretest-Posttest Designs

The two-group pretest-posttest design is considered to be the “classic” experimen-
tal design. Subjects are randomized to either the experimental group receiving
the intervention or the control group. They are measured before and after the
intervention is implemented (see Table 7-1). This design allows researchers
to examine within-subjects results as well as between-subjects results. For ex-
ample, a researcher wants to test a new teaching strategy for diabetic patients.

FYI

Experimental designs look for differences

between treated and untreated subjects.

The untreated group is the control group.

KEY TERM

two-group pretest-

posttest design:

Subjects are

randomly assigned

to the experimental

or control group

and are measured

before and after the

intervention; classic

or true experiment

Two-Group Pretest-Posttest (Classic)

Experimental Group R O 1 X O 2

Control Group R O 1 O 2

Two-Group Posttest-Only

Experimental Group R X O 1

Control Group R O 1

Solomon Four-Group

Experimental Group 1 R O 1 X O 2

Experimental Group 2 R X O 2

Control Group 1 R O 1 O 2

Control Group 2 R O 2

Crossover (Randomization of Treatment Order)

Experimental Group 1 O 1 O 2 R X 1 O 3 O 4 (–X) O 5 O 6 X 2 O 7 O 8

Experimental Group 2 O 1 O 2 R X 2 O 3 O 4 (–X) O 5 O 6 X 1 O 7 O 8

Note: R = randomization; O = observation or measurement; X = treatment or intervention;

–X = treatment withdrawn.

TABLE 7-1 Experimental Designs

7.1 Experimental Designs 173