CLASSIFICATION OF RESEARCH DESIGNS

      In selecting a research design for one's study, you may be guided by a simple classification system that defines all the variations to be considered.  This system looks at research designs as a complex concept that may be viewed from at least eight different perspectives, namely:

a) the degree to which the research problem hase been crystallized (the study may be exploratory or formal) b) the method of data collection (studies may be observational or survey)
c) the power of the researcher to affect the variables under study (the two major types of research are the experimental and ex post facto)
d) the purpose of the study (research studies may be descriptive or causal)
e) the time dimension (research may be cross-sectional or longitudinal)
f) the topical or the breadth and depth of the study (a case or a statistical study)
g) the research environment (field or laboratory setting)
h) subject's perception of the research (normal activity or deviation fro  everyday routines) (Emory,1991,p.12).

A.  DEGREE OF PROBLEM CONCEPTUALIZATION

      A study may be viewed as either exploratory or formal.  The essence of distinction between the two is the degree of structure and the immediate objective of the study.

      Exploratory studies tend to be loosely strucutured with an objective of learning what the major research tasks are to be.  The immediate purpose of exploration is usually to develop hypotheses or questions for future research.

      The formal study begins where the exploration leaves off.  It begins with a hypothesis or a question and involves precise procedures with data source specifications.  The goal of a formal research design is to test hypothesis or answer the research questions.  All studies have elements of both exploration and formality.

B.  METHOD OF DATA COLLECTION

      The method of data collection leads to the distincition between interrogation and monitoring processes.

      Interrogation involves asking questions and collecting responses by personal or impersonal means.  The collection may result from interview or telephone conversations, self-administered or self-report instruments sent through the mails or left in convenient locations or transmitted electronically or through some other means.

      Monitoring involves making observations.  Some examples would include a traffic count at an intersection, a search of library collection and an observation of the actions of a group of decision makers without trying to elicit responses from them.

C.  RESEARCHER'S CONTROL OF VARIABLES
     
      This factor would distinguish between the experimental and the ex-post facto research.  In an experiment, there is an attempt on the part of the researcher to control and/or manipulate the variables of the study.  Experimentation provides the most powerful support possible for a hypothesis of causation.

      In 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.  The researcher is limited to holding the factors constant by judicious selection of subjects according to strict sampling procedures and by statistical manipulation of findings.

D.  THE PURPOSE OF THE STUDY

      The purpose of the study would classify design into the descriptive and the causal.  If the research is concerned with finding out who, what and when or how much, then the study is descriptive.  If the study asks why, or how one variabel affects another, the study is causal.

E.  THE TIME DIMENSION

      The time factor is the element that makes the cross-sectional study different from the longitudinal.  The former is carried out only once and the study represents a "snapshot" of one point in time whereas in the latter, research investigates the same people over a long repetitive period of time and tracks changes that occur over time through extended observations.  It is more expensive than the cross-sectional study.

F.  THE TOPICAL SCOPE

      This factor classifies research design into the statistical and the case study.  Designed for breadth than depth, statistical studies attempt to capture adequate;y the characteristics of a population by making inferences from a sample of items.  Hypotheses are tested quantitatively rather than qualitatively.  Generalizations about findings are presented based on the representativeness of the sample and the validity characteristics of the design.  Case studies place more emphasis ona full contextual analysis of a limited number of events or conditions and their interrrelations.

G.  THE RESEARCH ENVIRONMENT

      Designs that take place under actual environmental conditions are field studies and under simulated  conditions are laboratory studies.  Simulation is replicating the essence of a system or process.

H.  SUBJECTS' PERCEPTIONS

      The subjects' perception that research is being conducted may have a bearing on the results of the study.  If subjects believe that something out of the ordinary is happening, they may behave less naturally.  If done like a candid camera, behavior is as natural as possible.