Experimental Versus Quasi-Experimental Designs
Week 5 Discussion 1 asks the following: “After reading Chapter 5 in the course text compare and contrast the similarities and differences between experimental and quasi-experimental designs. Describe the different ways in which an independent variable can be manipulated. Demonstrate application of the scientific method and ethical principles by explaining what dictates the selection of design (experimental versus quasi-experimental) and the type of manipulation used in a research study. Finally, give an example of a situation that could be studied with an experiment or quasi-experiment and assess the appropriateness of one design over the other in light of practical and ethical concerns”.Experimental Versus Quasi-Experimental Designs
Keywords: experimental design, quasi-experimental designs.
The similarities between experimental and quasi-experimental designs are that study participants are subjected to some type of treatment or a condition, measure some outcome of interest, and the researchers test if the differences in the outcome are related to the treatment. There are also some differences between experimental and quasi-experimental designs. In experimental design, study participants are randomly assigned to either the treatment or the control group, whereas participants are not assigned randomly in a quasi-experiment. Quasi-experiment is often described as nonrandomized, pre-post intervention study (Harris, 2006). In a quasi-experiment, the control and treatment groups vary not only in terms of the experimental treatment that was provided to them, but also in other ways (the Research Connections, 2016). In quasi-experimental design, the variables are only measured and cannot be manipulated by the researcher because of the lacks of control. An independent variable can be manipulated in many ways by changing the environment and manipulation (change the size, frequency, the level of intensively, etc.). Researchers can measure the differences from the dependent variable to change the independent variable. In experimental research design, the researchers manipulate the factor (treatment or intervention) that is hypothesized to influence the outcome. Researchers can manipulate the treatment the research participants receive or the level of this treatment.
The experimental design is probably the strongest design when it concerns external validity (Newman, 2011). The quasi-experimental design lacks random allocation of groups or proper control, thus statistical analysis may be very challenging. In conclusion, I provide an example of a situation, how smoking affects women’s pregnancy and fetus, that could be studied with a quasi-experiment. It is obvious that the researchers cannot randomly select and involve pregnant women to smoke (it is unethical), which is necessary for the true research. Thus, the study participants should provide some information or report about how much they smoked during their pregnancy. After that, the researchers can classify the participants into groups (based on self-reports), collect data, and do statistical testing without harming any pregnant women. Experimental Versus Quasi-Experimental Designs
References:
Experiments and Quasi-Experiments (2013). Childcare and Early Education Research Consultants. Retrieved from http://www.researchconnections.org/childcare/datamethods/experimentsquasi.jsp
Newman, M. (2011).Research methods in psychology. San Diego, CA: Bridgepoint Education Inc.
Harris, A., McGregor, J., Perencevich, E., Furuno, J., Zhu, J., Peterson, D., & Finkelstein, J. (2006). The use and interpretation of quasi-experimental studies in medical informatics. Journal of the American Medical Informatics Association, 13(1), 16-23.Experimental Versus Quasi-Experimental Designs