CHOOSING A RESEARCH DESIGN
by Ilham
Lecturer of English Dept University of Muhammadiyah Mataram
Choosing an appropriate research design is crucial important to the success of your project. The decision that you make at this stage of the research process do much to determine the quality of the conclusions that you can draw from your research results. This writing involves the problem that you must face when choosing a research design, introduces the major types of research design and describe how each type attempts to solve.
Function of a Research Design
Scientific studies tend to focus one or the other of two major activities. The first activity consist of exploratory data collection and analysis, which is aimed at classifying behaviors within a given area of research, identifying potentially important variables, and identifying relationships between those variables and the behaviors. The second activity, called hypothesis testing, consists of evaluating potential explanations for the observed relationship. Testable explanations allow you to predict what relationship should and should not be observed if the explanation is correct.
Causal Versus Correlational Relationships
In causal relationship, one variable directly or indirectly influences another. In other words, changes in the value of one variable directly or indirectly cause changes in the value of a second. Causal relationships can be unidirectional, in which case variable A influences variable B but not vice versa. They also can be bidirectional in which case each variable influence the other.
In a correlational relationship, changes in one variable accompany changes in another, but the proper test have not been conducted to show that either variable actually influences the other. When changes in one variable tend to be accompanied by specific changes in another, the two variables are said to covary.
Correlational Research
Correlational research belong to a broader category called non-experimental research, which also includes design not specifically aimed at identifying relationships between variables. Correlational research involves observing the values of two or more variables and determining what relationship exist between them. In correlational research, you make no attempt to manipulate variables but observe them “ as is”.
In their simplest form, correlational studies investigate the possibility of relationships between only two variables, although investigations of more than two variables are common. In contrast to experimental research, however, there is no manipulation of variables in correlational research.
Correlational research is also sometimes referred to as a form of descriptive rerserach because it describes an existing relationship between variables. The way it describes the relationship, however, it quite different from the description found in other types of studies. A correlational study describes the degree to which two or more quantitaives variables are related, and it does so by using a correlation coefficient.
When correlation is found to exist between two variables, it means that scores within a certain range on one variable are associated with scores within a certain range on the other variable. You will recall that positive correlation means high scores on one variable tend to be associated with high score on the other variable, while low scores on one are associated with low scores on the other. A negative correlation, on other hand, means high score on one variable are associated with low scores on other variable, and low score on one are associated with high score on the other (Fraenkel and Wallen, 2007).
Why Use Correlational Research
There are three situations in which a correlational approach makes good sense:
- gathering data in the early stages of research. During the initial, exploratory stage of a research project, the correlational approach’s ability to identify potential causal relationships can provide a reach source of hypotheses that later may be tested experimentally.
- In ability to manipulate Variables. In an experimental design, variables are manipulated to determine their affect on other variables. A second reason for choosing a correlational design over an experimental one is that manipulating the variables of interest may be impossible or unethical.
- Relating Naturally occurring variables. Correlational research design may be chosen over an experimental design is one in which you want to see how naturally occurring variables relate in the real word. Such information can be used to make useful predictions even if the reasons for the discovered relationships are not clear. High school GPA, scores on the SAT, class rank, and scores on the Nelson-Denny Reading comprehension test correlate well with each other and with performance in college. Knowledge of these relationships has been used to predict college success. Certain theoretical views also may lead to prediction about which real word variables should be correlated with which.
Reference
Bordens, K.S. and Abbott, B.C. 2008. Research Design and Method. New York: McGraw-Hill.
Cohen,L. and Manion, L. 1994. Research Method in Education (fourth Edition). USA: Routledge.
Fraenkel and Wallen. 2007. How to Design and Evaluate Research in Education. New York: McGraw-Hill Companies, Inc.
Gay.L.R. 1992. Educational Research. Competencies for Analysis and Application. United States of America: Macmillan publishing company.
