Static Group Design

In 1963, Donald Campbell and Julian Stanley initially designated the static group design, one of the three preexperimental designs. Preexperimental designs are best thought of as premature designs in that they have serious flaws and therefore should be avoided. The static group design is also called the posttest-only nonequivalent groups design. Consistent with this name, participants are nonrandomly assigned into two groups (experimental vs. comparison). Participants then take a posttest after receiving treatment. Importantly, there is no pretest, so it is impossible to ascertain whether any group differences are due to the experimental manipulation/treatment or preexisting differences.

Preexperimental designs such as the static group design are typically used to explore a relationship prior to a true experiment, although they are occasionally used in applied research after more rigorous experimental research has established a causal relationship. Preexperimental designs are the simplest type of research design, and they use existing groups (i.e., no random assignment). In contrast to the other two preexperimental designs, the static group design introduces a comparison group. However, participants are not randomly assigned to the control and treatment groups. This flaw, along with the lack of a pretest, makes it difficult if not impossible to establish a causal relationship.

Among the list of factors that could jeopardize the internal validity of an experiment, the static group design appears to be vulnerable to three: selection, mortality, and maturation. With regard to selection, it is possible that there might be systemic differences between the groups prior to treatment. Mortality refers to the notion that the posttest might reflect differences in the dropout rate between the experimental and control groups rather than the treatment. Somewhat similar to mortality, maturation points to the likelihood that changes in the internal states of the participants might account for differences in the posttest rather than the treatment. These threats to validity are the static group design’s biggest disadvantages and the reason this design is primarily used for exploratory purposes.

The static group design is sometimes used out of necessity rather than exploratory or negligent science. Occasionally, ethical considerations would prevent researchers from imposing a treatment or variable of interest upon participants. Consider, for example, a researcher who would like to study the effects of in utero maternal drug use on newborn infants. The researcher cannot ethically randomly assign mothers to drug use and nondrug use conditions nor can the researcher give a pretest to the infants. The static group design becomes the flawed, but only option. Ideally, the comparison group should be matched as closely as possible to the experimental group.

Although the static group design has some serious limitations (i.e., threats to internal validity), it can be a cost-effective, ethical, and/or exploratory way to obtain prima facie evidence of a treatment effect. Notwithstanding, any conclusions drawn from a study that has utilized this design must be tentative and interpreted with caution. For this reason, it is best to follow up any study that has used this design with a replication study that utilizes a more rigorous true experimental design.

...