The following module provides an overview of quasi-experimental research.
Define quasi-experimental research
Compare and contract experimental research and quasi-experimental research
Describe appropriate uses of quasi-experimental research
Provide examples of research projects where the use of quasi-experimental techniques can be beneficial
The following video, Classifying Quantitative Research Designs: Descriptive non-experimental, Quasi-experimental or Experimental, is a great place to begin exploring quasi-experimental research. Comparing and contrasting several types of quantitative research designs helps to define quasi-experimental research and describe its appropriate uses and applications.
Quasi-experimental and true experimental research designs both attempt to determine causal relationships by applying a treatment or condition to one group and comparing the outcome with a control group. A true experimental design is the gold standard in assessing causal relationship because it requires that subjects be randomly assigned to the groups to avoid bias and it controls all extraneous variables. Sometimes, however, it may not be possible to randomly assign test subjects to the treatment and control groups for a variety of practical or ethical reasons. It may be that the test subjects are not easily classified, there may be time constraints, assignment may create an artificial situation, or logical test groups may already exist. Therefore, quasi-experimental research is used extensively in social science, psychology, education, and medical research. For example, if a researcher wanted to study the impact of an educational intervention on two 5th grade classrooms, it may be disruptive to attempt to rearrange the students in an existing class by randomly re-assigning them. Clinical research is another area where quasi-experimental research is commonly used. If studying the side effects of a new medicine compared to a previously prescribed medication, researchers would have to use those currently taking the new medication as the treatment group because it would be unethical to randomly assign others into the treatment group and have them take a medication that may have harmful effects. Similarly, if a researcher was studying the impact of solitary confinement on inmates in a federal prison; it would be unethical to randomly assign other prisoners to the treatment group. These examples illustrate why quasi-experimental research is sometimes referred to as experimental research that occurs in its natural setting.
The quasi-experimental research design does have a disadvantage in that the subjects are not randomly assigned and hence, there is some loss of control over extraneous variables that may impact the study. The lack of random assignment raises the question of how similar or dissimilar the treatment and comparison groups were from the outset in terms of baseline characteristics. For this reason, the results of quasi-experimental research are sometimes referred as a “trend” versus a “cause”. However, anytime that human subjects are involved, there is never a complete guarantee that differences in opinions and the practices of the individuals will not affect the outcome. Therefore, it is important to focus on the strengths of the quasi-experimental design. Quasi-experimental designs offer a broader scope of design and allow the research to occur in its natural setting. The validity of quasi-experimental research can be improved by specific methods that assist in identifying a comparison group, controlling bias, and using appropriate statistical analyses.
In summary, quasi-experimental research may be described by the key points listed below. These issues will be discussed in more detail in the next modules in this series.
Quasi-experimental research designs test causal relationships, much like true experimental designs.
A quasi-experimental design lacks the random assignment that is a requirement of true experimental research.
Quasi-experimental designs attempt to remedy this issue by using methods to identify a comparison that is as similar as possible to the treatment group.
There are specific techniques that should be used to create a valid comparison group.
Quasi-experimental research uses a broader array of data collection techniques and statistical analyses than true experimental research.
Bernard, H. R., & Bernard, H. R. (2012). Social research methods: Qualitative and quantitative approaches. Sage. Brown, L. (2010). Quasi-experimental research. Doing Early Childhood Research: International perspectives on theory and practice, 345. Campbell, D. T., & Stanley, J. C. (2015). Experimental and quasi-experimental designs for research. Ravenio Books. Creswell, J. W. (2013). Research design: Qualitative, quantitative, and mixed methods approaches. Sage publications. Lipsey, M. W. (1990). Design sensitivity: Statistical power for experimental research (Vol. 19). Sage. Punch, K. F. (2013). Introduction to social research: Quantitative and qualitative approaches. Sage. William R.. Shadish, Cook, T. D., & Campbell, D. T. (2002). Experimental and quasi-experimental designs for generalized causal inference. Wadsworth Cengage learning.