Having discussed the nature of the scientific method and the steps involved therein, we now turn to research design. Our first subject here is to clarify what is meant by “design” in the research context—and what it comprises. Then we will describe just what designs accomplish in relationship to the total research process. An important distinction then will be drawn between experimental and nonexperimental designs.
According to Kirlinger: Research design is the plan, structure, and strategy of investigation conceived so as to obtain answers to research questions and to control variance.
The definition consists of three important terms – plan, structure and strategy. The plan is an outline of the research scheme on which the researcher is to work. The structure of the research is a more specific outline or the scheme and the strategy shows how the research will be carried out, specifying the methods to be used in the collection and analysis of data.
Let us look into a few other definitions of research design. Bernard S. Philips has defined the research design as: … the blueprint for the collection, measurement and analysis of data. It aids the scientist in the allocation of his limited resources by posing crucial choices – Is the blueprint to include experiments, interviews, observation, the analysis of records, stimulation, or some combination of these? Are the methods of data collection and the research situation to be highly structured? Is an intensive study of a small sample more effective than a less intensive study of a larger sample? Should the analysis be primarily quantitative or qualitative?
According to Green and Tull: A research design is the specification of methods and procedures for acquiring the information needed. It is the over-all operational pattern or framework of the project that stipulates what information is to be collected from which sources by what procedures.
From the foregoing definitions it is evident that research design is more or less a blueprint of research. It can be compared with the plan of house, which lays down the method and procedure for the collection of requisite information and its measurement and analysis with a view to arriving at certain meaningful conclusions at the end of the proposed study.
The Nature of Research Designs: The noun “design” has various meanings, but the one suitable for our subject is a pattern or an outline of a research project’s workings. It is a statement of only the essential elements of a study, those that provide the basic guidelines for the details of the project. It comprises a series of prior decisions that, taken together, provide a master plan for executing a research project.
A master plan is comprehensive and gives a general statement of the methods to be used, in contrast to the details that should be written to be sure of the specific work to be done (and to be assigned to the staff or outside suppliers). A research design has some similarly to a description of a “model”.
What is contained in a design may vary depending on the preference of the person responsible. It should be confined to the minimum of detail that is required for planning. It should include at least the following.
- Statement of the study’s objectives, the output of the researcher in conclusive studies, this result is expected to solve the problem.
- Statement of the data inputs, or causal data, on the basis of which the solution is to be reached
- The analytical method with which the inputs will be treated or calculated.
These three elements are illustrated in a very simple case, as follows:-
The Albus Company (which is imaginary) sells a broad line of Kitchen and household utensils by mail order. On of the managers believes that profits could be increased by inducing customers to order more on each purchase. The incentive would be offer a bonus of 10 percent additional merchandise on all orders above $ 25.00. The other Albus managers are doubtful and so the hypotheses are to be rested by research. The design for that would have the three elements as described here.
- The objective is to calculate the dollar margin change (price minus shipping costs and merchandise costs) earned on sales where the bonus is offered.
- The data to be gathered are (a) dollar sales on order placed by a sample of customers who are offered the bonus and by another (equal sized) sample to whom it is not made available, (b) average merchandise margins earned during the period of the test (that of the spring catalog), (c) cost of the free bonus merchandise ordered during the period, and (d) cost of promotional inserts.
- The analysis of those data will be
- Dollar sales to sample A minus those to sample B, during period of March 1-July 31, multiplied by average merchandise margin earned during that period.
- Subtract dollar cost of merchandise sent as bonuses to sample A.
- Subtract also shipping costs of bonus merchandise and costs of promotional pamphlet.
Designs should comprise only what researcher’s need for a framework that is sufficient to (1) flesh out the details for costing and implementing the work and (2) explain the proposed study to others.
Benefits of Designs
A researcher design serves as a bridge between what has been established (the research objective) and what is to be done, in the conduct of the study, to realize those objectives. It anticipates what the client will need in terms of results and the analytical work on the gathered data that will convert it to useful findings.
If there were no explicit design, the researcher would have only foggy motion about what to do. It is extremely desirable that the design be put in writing, for it is obvious how a study may go astray when its concepts exist only in the researcher’s memory. And unless the researcher is able to state the design in clear and written terms, it is questionable whether he or she truly understands what is to be done or why.
A formal design’s benefits are particularly appreciated when the researcher is deciding specifically what data are needed. If data are gathered that prove to be irrelevant, that is both inefficient and confusing. It is even more serious to have overlooked some data that are vitally needed, which may not be discovered until too late, at the analytical stage.
A design also is appreciated when analyzing the data and interpreting their meaning. It helps to keep the computations and thinking on the path to solutions and recommendations. However, we are not suggesting that a design be a rigid framework. A design had been decided on the basis of expectations, but surprises will be met as the study unfolds, in the character and availability of data and in new hypotheses that turn up during analysis. In short, the original design guides, but does not dictate, the conduct of the research.
The mail-order example, we may note, is a quantifiable example. It could be written in algebraic symbols rather than our long verbal description, which many would prefer. Descriptive studies do not produce quantifiable data of course, and so their designs would be described verbally.
