There are many definitions of research design, but no definition imparts the full range of important aspects. Kerlinger N F (1986) defines a research design as the plan and structure of investigation so conceived on to obtain answer to research questions. The plan in the overall scheme or program of the research; It includes an outline of what the investigator will do from hypothesis and their operational implication to the final analysis of data. A structure is the framework, organization, or configuration of….; the relations among variables of a study. A research design expresses both the structure of the research problem and the plan of investigation
used to obtain empirical evidence on relations.
Phillips S B (1971) noted that the research design constitutes 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, simulation, 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 efficient that a less intensive study of a large sample? Should the analysis be primarily quantitative or qualitative?
The two definitions differ in detail, but together they give the essentials of research design First, the design is a plan for selecting the sources and types of information used to answer the research question(s).
Second, it is a framework for specifying the relationships among the study’s variables.
Third, it is a blue print that outlines each procedure from the hypothesis to the analysis of data. The design provides answers for such questions as these.
- What techniques will be used to gather data?
- What kind of sampling will be used?
- How will time and cost constraints be dealt with?
In a nutshell, the purpose of the research design is two fold:-
- Provide answers to the research question(s)
- Introduce a kind of orderliness in the process of answering the question(s)
A good research design is therefore the one that enables one to answer the research question validly, objectively, accurately and economically. It is one that also enables one to provide empirical data to the research question(s). There are many research designs as there are many approaches to hypothesis testing.
One wants to have a design that provides dependable and valid answers.
Classification of Designs
Early in any research study, one faces the task of selecting the specific design to use. A number of different design approaches exist, but unfortunately no simple classification system defines all the variations that must be considered. Cooper and Schindler have
classified research design using at least eight different descriptions.
1. The degree to which the research question has been crystallized (the study may be either exploratory or formal).
2. The method of data collection (studies may be observational or communication based).
3. The power of the researcher to produce effects in the variables under study (the two major types of research are experimental and ex post facto).
4. The purpose of the study (research studies may be descriptive or casual)
5. The time dimension (research may be cross-sectional or longitudinal).
6. The topical scope – breadth and depth – of the study (a case or statistical study).
7. The research environment (most business research is conducted in a field setting, although laboratory research is not unusual; simulation is another option.
8. The subjects’ perceptions of the research (do they perceive deviation from their everyday routines).
A brief discussion of these descriptors illustrates their nature and contribution to research.
1. Degree of Research Question Crystallization
A study may be viewed as exploratory or formal. The essential distinction between these two is the degree of structure and the immediate objective of the study. Exploratory studies tend toward loose structures with the objective of discovering future research tasks. The immediate purpose of exploration is usually to develop hypotheses or questions for further research. The Formal Study begins where the exploration leaves off – it begins with a hypothesis or research question and involves precise procedures and
data source specifications. The goal of a formal research design is to test the hypotheses or answer the research questions posed.
The exploratory-formalized dichotomy is less precise than some other classifications. All studies have elements of exploration in them, and few studies are completely uncharted.
2. Method of Collection
This classification distinguishes between monitoring and interrogation/communication process. The former includes observational studies, in which the researcher inspects the activities of a subject or the nature of some material without attempting to elicit responses from anyone. Traffic counts at an intersection, a search of the library collection, an observation of the actions of a group of decisionmakers – are all examples of monitoring. In each case the research notes and records the information available from observations.
In interrogation/communication mode, the researcher questions the subjects and collects their response by personal or impersonal means. The collected data may result from:
- Interview or telephone conversations.
- Self-administered or self-report instruments sent through mail, left in convenient locations, or transmitted electronically or by another means, or
- Instruments presented before and/or after a treatment or stimulus condition in an experiment. (We use the term communication to contrast with observational because collecting data by questioning encompasses more than
the ‘survey method).
3. Researcher Control of Variables
In terms of the researcher’s ability to manipulate variables, we differentiate between experimental and ex post facto designs. In an experiment, the researcher attempts to control and/or manipulate the variables in the study. It is enough that we can cause
variables to be changed or held constant in keeping with our research objectives. Experimental design is appropriate when one whishes to discover whether certain variables produce effects in other variables. Experimentation provides the most powerful
support possible for a hypothesis of causation.
With an ex post facto design, investigators have no control over the variables in the sense of being able to manipulate them. They can only report what has happened or what is happening. It is important that the researcher using this design not influence the
variables; to do so introduce bias. The researcher is limited to holding factors constant by judicious selection of subjects according to strict sampling procedures and by statistical manipulation of findings.
4. Purpose of Study
The essential difference between descriptive and casual studies lies in their objectives. If the research is concerned with finding out who, what, where, when, or how much, then the study is descriptive. If it is concerned with learning why – that is how one variable
produces changes in another – it is casual. Research on crime is descriptive when it measures the types of crimes committed, how often, when, where, and by whom. In a casual study, we try to explain relationships among variables – for instance, why the
crime rate is higher in city A than in city B.
5. The Time Dimension
Cross-sectional studies are carried out once and represent a snapshot of one point in time. Longitudinal studies are repeated over an extended period. The advantage of a longitudinal study is that it can track over an extended period. The advantage of longitudinal study is that it can track changes over time. In longitudinal studies of the panel variety, the researcher may study the same people
over time. In marketing, panels are set up to report consumption data on a variety of products. These data, collected from national samples, provide a major data bank on relative market share, consumer response to new products, and new promotional
methods. Other longitudinal studies, such as cohort groups, use different subjects for each sequenced measurement. The service industry might have looked at the needs of aging baby boomers by sampling 40 to 45-year olds in 1990 and 50 to 55-year olds in
2000. Although each sample would be different, the population of 1945 to 1950 cohort survivors would remain the same.
Some types of information once collected cannot be collected a second time from the same person without the risks of bias. The study of public awareness of an advertising campaign over a six-month period would require different samples for each measurement.
While longitudinal research is important, the constraints of budget and time impose the need for cross-sectional analysis. Some benefits of a longitudinal study can be assured by adroit questioning about past attitudes, history, and future expectations. Response to these kinds of questions should interpret with care, however.
6. The Topical scope
The statistical study differs from the case study in several ways. Statistical studies are designed for breadth rather than depth. They attempt to capture a population’s characteristics by making inferences from a sample’s characteristics. Hypotheses are tested quantitatively. Generalizations about findings are presented based on the representativeness of the sample and the validity of the design. Case studies place more emphasis on a full contextual analysis of fewer events or conditions and their interrelations. Although hypotheses are often used, the reliance on qualitative data makes support or rejection more difficult. An emphasis on detail
provides valuable insight for problem solving, evaluation, and strategy. This detail is secured from multiple sources of information. It allows evidence to be verified and avoids missing data.
Although case studies have been maligned as ‘scientifically worthless’ because they do not meet minimal design requirements for comparisons, they have a significant scientific role. It is known that ‘important scientific propositions have the form of universals, and a universal can be falsified by a single counter-instance. Thus, a single, well-designed case study can provide a major challenge to a theory and provide a source of new hypotheses and constructs simultaneously.
7. The Research Environment
Designs also differ as to whether they occur under actual environmental-conditions or under other conditions. These are called field conditions and laboratory conditions, respectively. To stimulate is to replicate the essence of a system or process. Simulations are being used more in research, especially in operations research. The major characteristics of various conditions and relationships in actual situations are often represented in mathematical models. Role playing and other behavioral activities may also be viewed as simulations.
8. Subjects’ Perceptions
The usefulness of a design may be reduced when people in the study perceive that research is being conducted. Subjects’ perceptions influence the outcomes of the research in subtle ways. Although there is no widespread evidence of attempts to please researchers through successful hypothesis guessing or evidence of the prevalence of sabotage, when subjects believe that something out of the ordinary is happening, they may behave less naturally.
There are three levels of perception;
- Subjects perceive no deviations from everyday routines.
- Subjects perceive deviations, but as unrelated to the researcher.
- Subjects perceive deviations as researcher induced.
In all research environments and control situations, researchers need to be vigilant to effects that may alter their conclusions. These serve as reminder to classify one’s study by type to examine validation, strength and weaknesses, and be prepared to qualify results accordingly.