Research Methods Literature Review PLEASE SEE DOCUMENTS NEEDED ATTACHED!!!

Everleigh

posttest_onlycontrolgroup_quantitativeexperimental.pdf

Home >Psychology homework help >Research Methods Literature Review PLEASE SEE DOCUMENTS NEEDED ATTACHED!!!

Posttest-Only Control Group Design

In: The SAGE Encyclopedia of Educational Research,

Measurement, and Evaluation

By: Grant B. Morgan & Rachel L. Renbarger

Edited by: Bruce B. Frey

Book Title: The SAGE Encyclopedia of Educational Research, Measurement, and Evaluation

Chapter Title: "Posttest-Only Control Group Design"

Pub. Date: 2018

Access Date: August 16, 2021

Publishing Company: SAGE Publications, Inc.

City: Thousand Oaks,

Print ISBN: 9781506326153

Online ISBN: 9781506326139

DOI: https://dx.doi.org/10.4135/9781506326139

Print pages: 1279-1281

This PDF has been generated from SAGE Research Methods. Please note that the pagination of the

online version will vary from the pagination of the print book.

https://dx.doi.org/10.4135/9781506326139

The posttest-only control group design is a research design in which there are at least two groups, one of

which does not receive a treatment or intervention, and data are collected on the outcome measure after

the treatment or intervention. The group that does not receive the treatment or intervention of interest is

the control group. The general process for this design is that (a) two or more groups are formed; (b) the

treatment or intervention is administered; (c) data are collected after the treatment or intervention has been

administered, commonly using a behavioral, cognitive, or psychological assessment; and (d) the data are

compared between groups to determine whether the treatment or intervention was effective. The goal of this

design is often to make causal inferences; that is, to draw conclusions about whether or not a difference

between groups (i.e., the effect) is observed as the result receiving the intervention (i.e., the cause). This

entry presents considerations for using the posttest-only control group design for causal inference, discusses

the advantages and limitations of this method, and provides an example.

Considerations for Causal Inference

The three commonly referenced conditions that must be met in order to infer causality are (1) temporal

precedence of proposed cause and effect, (2) covariation of proposed cause and effect, and (3) elimination

of alternative explanations for the effect. For the first condition to be met, the treatment or intervention must

occur before differences between groups on the outcome variable (i.e., the effect) are observed. The posttest-

only control group design is able to meet this condition because the treatment or intervention is administered

before the potential group differences are observed. For the second condition to be met, it must be possible

for the researcher to determine what happens both when the treatment or intervention is present and when it

is absent. Again, the posttest-only control group design is able to meet this condition because it includes at

least one treatment or intervention group and one control group. For the third condition to be met, potential

alternative explanations for differences in group outcomes must be accounted for or ruled out. The posttest-

only control group design may, but does not necessarily, meet this condition.

To minimize such alternative explanations, groups are formed using random assignment, so that any

differences between groups that are observed before the administration of treatment or intervention will

be due to randomness. Ideally, there will be no preexisting group differences due to random assignment

and/or matching of some sort. The determining factor is how the groups are formed; if they are formed

using random assignment with matching (in which the researcher creates pairs of participants, one from the

treatment group and one from the control group, who have comparable important characteristics beyond

group membership) or without, then the posttest-only control group design is able to meet this condition.

If the groups are formed using a nonrandom mechanism (e.g., convenience, self-selection of participants

into groups, criterion-based inclusion, or already-existing groups), then the posttest-only control group design

cannot meet this condition. The way groups are formed for comparison is of crucial importance for inferring a

causal relationship between the treatment or intervention and the observed differences between groups. For

the types of research questions that lend themselves to posttest-only control group design, causal inference

is commonly the desired outcome, so random assignment with or without matching is recommended.

SAGE

SAGE Research Methods

Page 2 of 5 Posttest-Only Control Group Design

Advantages

The posttest-only control group design is commonly compared against the pretest–posttest control group

design. Because no data are collected before the administration of the treatment or intervention (i.e., no

pretest), the posttest-only control group design requires fewer resources (e.g., time, money, energy) for

data collection. In fact, collecting data prior to a treatment or intervention may not be possible or feasible.

Furthermore, the process of collecting pretest data may prepare participants or give them clues into the

intended effect of treatment or intervention (referred to as a testing threat to internal validity). This may affect

the way participants interact with the actual treatment or intervention compared with how they would have

acted without prior knowledge in a posttest-only design.

Limitations

There are a number of limitations of the posttest-only control group design. These limitations are primarily

related to not being able to rule out alternative explanations. First, regardless of how groups are formed, it

is possible that the treatment group(s) differ from the control group before any treatment or intervention is

ever administered. If this is the case, there is no mechanism in place to provide evidence of these differences

because no data were collected ahead of the treatment or intervention. Unknown preexisting differences may

well affect the effectiveness of the treatment or intervention in some way. Such preexisting differences may

result in the researcher reaching an incorrect conclusion about observed group differences being attributable

to the treatment or intervention.

A second limitation associated with the posttest-only control group design is maturation threat, which is a

more common threat to causal inferences in longer studies. Maturation refers to how people change over the

course of time, whether it be emotionally, physically, or mentally. Although the length of the study is usually

not long enough for people to naturally change in a meaningful way, the absence of a pretest prevents the

researcher from being able to collect data on the natural change of participants over the course of the study.

The expected growth of participants over the course of the study can only be assessed by examining the

change of the control group. As a result, the posttest-only control group may be subject to the maturation

threat on causal inference.

As noted earlier, the posttest-only control group design involves two or more groups, one of which is the

control group. As a result, the design is subject to certain limitations related to multiple groups. These

limitations have been referred to as social interaction threats to the inferring causal relationship(s), and many,

if not all, research designs involving multiple groups are subject to these same limitations.

The first of the multiple-group limitations is diffusion of treatment. This occurs when participants in the

control group receive the treatment or intervention from participants in the treatment or intervention group

directly or through some other means, and the control group adopts or tries to replicate the treatment or

intervention in their own group. The second of the multiple group limitations is rivalry. If the participants in

SAGE

SAGE Research Methods

Page 3 of 5 Posttest-Only Control Group Design

each group know which group(s) their scores are being compared against, the group members may begin to

compete with each other, thus affecting the results of the group comparisons. The third of the multiple-group

limitations is equalization of treatment, which occurs when there is some perceived desirability, value, or

inequity associated with being in the treatment or intervention group. If this is the case, there may be internal

or external pressure to reassign participants to the treatment or intervention or to administer it to everyone

to promote fairness. Obviously, this would interfere with the design’s ability to demonstrate the effectiveness

of the treatment or intervention. The last of the multiple-group limitations is resentful demoralization, which

occurs when participants in the control group become aware that they are not receiving the treatment

or intervention and, being demoralized by this discovery, attempt to sabotage the research. For example,

they may perform worse on the assessments than they would ordinarily, artificially increasing the observed

differences between groups.

Example

Two scenarios within the same context are presented here to demonstrate the posttest-only control group

design and its implications on how the treatment and control groups are formed. Suppose a fifth-grade

teacher hypothesizes that learning and practicing chess will increase math achievement in students who

participate in an afterschool program. She decides to collect data that will allow her to test her hypothesis.

In the first scenario, she randomly chooses half of the students in the afterschool program to learn and

practice chess, and she administers the program with fidelity for 4 weeks. At the end of the 4-week period,

she administers a math assessment with demonstrated reliability and validity evidence to all students in the

afterschool program—those who participated in the chess program and those who did not. The students who

participated in the chess program received higher math scores than those who did not. This scenario is an

example of a posttest-only control group design. In a second scenario, the teacher allows any student who is

interested to participate in the chess program. After students self-select into the program, she administers the

program with fidelity for 4 weeks. At the conclusion of the 4-week period, she administers a math assessment

to all students in the afterschool program—those who participated in the chess program and those who did

not. Those who participated in the chess program had higher math scores than those who did not participate

in the chess program. This is also an example of a posttest-only control group design.

With which scenario would you feel more comfortable concluding that the observed differences in math

achievement was attributable to the chess program? In the first instance, the groups were formed through a

random process, and any differences that existed between the group members were therefore due to chance.

In the second scenario, the groups self-selected into or out of the chess program, and as a result, there

are known differences between the group members, namely, interest in chess. Therefore, the program may

have a different effect for those students than it would have had for “typical” students. As a result, it would

be impossible to separate the interaction between interest in chess and effect of chess on the observed

difference in posttest math achievement.

For the purposes of this entry, the posttest-only control group design is exemplified through these two

SAGE

SAGE Research Methods

Page 4 of 5 Posttest-Only Control Group Design

scenarios. As demonstrated, it is important to consider the threats to internal validity in the use and decision

making associated with this research design.

See also Analysis of Variance; Causal Inference; Experimental Designs; Nonexperimental Designs;

Pretest–Posttest Designs; Random Assignment; t Tests

Grant B. Morgan & Rachel L. Renbarger

http://dx.doi.org/10.4135/9781506326139.n530

10.4135/9781506326139.n530