There are as many types of research designs as there are types of research. For the purpose of this guide, this section provides an overview of the major types of research and designs that are commonly adopted by the students of research and practitioners. The designs are broadly classified into two: descriptive and Experimental research designs.
Experimental Research Designs
Experimental research designs rely on random assignment and laboratory controls to ensure the most valid, reliable results; they produce the strongest, most valid results. However, the experimental design is often not practical for many studies in social science, education and business because researchers cannot, in many instances, exercise laboratory controls in natural-world settings or randomly assign subjects. An experimental design consists of two groups of subjects: an experimental group and a control group. The experimental group undergoes the treatment, program or intervention of interest. Researchers then measure the differences between the two groups on a particular outcome.
Strengths and weakness: Experimental research design has its strengths and drawbacks. The greatest strength of an experimental-research design is the highest level of certainty with which changes in the outcome of interest which can be attributed to the independent variable or “treatment.” The greatest drawback of the design is its artificiality, for effects occurring in an experiment under research controls might not take place in more natural settings.
There are three types of true experimental designs. These include:
- Pre-test-Post-test control group design
- Post-test only control group design
- Solomon Four-Group design
Quasi Experimental Research Design
Quasi experimental design specifically lacks the element of random assignment to treatment or control; allows the researcher to control the assignment to the treatment condition, but using some criterion other than random assignment. Quasi experiments are usually preferred where other experiments might not be practical since true experiments cannot answer the many questions that one would want to.
References
