Anda di halaman 1dari 10

CORRELATIONAL RESEARCH

Abstract Correlational is a kind of quantitative research to discover relationships between two or more variables. The research guide to understand related events, conditions, and behaviors and to make predictions of how one variable might predict another. The research has four chacacteristics; it is suitable if the variables are complicated or can not be researched by experimental method or can not be manipulated;it is enable in measuring some variables and the relations in advanced for its real condition; the output of the research is a level or the high and low of relation and not the presence or absence of those relation;the researh may predict certain variables based on independent variable. Fields of Correlational Research are Relation Research; Predictive Research; Multivaried Correlation Correlational Research Design are Bivariate correlation; Regression and Prediction;multiple regression;factor analysis; Correlational design to draw a causal conclusion;and system analysis. The research required the main design of problem determination; problem review or literary review; research design or research method; data collecting;data analysis and conclusion. The advantage of the research are; able to investigate the relation among variables simultaneously; and give the information of its level or strength of relation among variables researched; able to investigate some variables intensively and able to do prediction analysis without mass sample. The disadvantage of the research are; the result is just to identify as the way it is and not showing any causalty relation; correlational research is less strict rules since the minority of controlling independent variables; the research oftenly used as short gun approach. I. Introduction Research is a science activity based on problem that needs right solution. In our daily life there are always problem to solve though not all of them will be solved through research. The basic components of a reserch are problem and research purpose thus we may find the right method to solve the problem. In general, research may differ in some aspects; purpose aspect, method aspect, study aspect. According to Gay ( in Sukardi, 2004:13) Purpose aspect consist of basic research and extend. Method aspect consist of descriptive, history research, survey research, ex-postfacto research, and experimental research whereas study aspect as the fields of research consist of educational research and non-educational research (Sukardi, 2004:13-16). Research matter may divide into certain fields like education, health, social, economics, etc. one of the field that need special treatment is education research. Generally there are two kinds of problem solving method in education, they are qualitative and quantitative. Qualitative method collect the data by direct interaction with the research object and the result is not drawn by statistics procedure. Quantitative research collect the data by research instrument that is population and sample hence the result drawn by statistics

procedure.

Correlational research is one of quantitative research and is useful as well

important in research in education. In the field of education there are many variables that are correlate each other like teacher and student, teacher and the curriculum, the material with the evaluation etc. research method. II. Correlational Research In general, a correlational study is a quantitative method of research in which we have 2 or more quantitative variables from the same group of subjects, and we are trying to determine if there is a relationship or covariation between the 2 variables a similarity between them, not a difference between their means. Theoretically, any 2 quantitative variables can be correlated for example, midterm scores and number of body piercings as long as we have scores on these variables from the same participants; however, it is probably a waste of time to collect and analyze data when there is little reason to think these two variables would be related to each other. According to Gay (1981:183) correlational research may treated as descriptive research, mainly caused by correlational research is describing a recent condition. Nevertheless, they are outstandingly different from self description or observation study. A correlational research describe how the variables are correlate. Correlational research is a research to find out the relation and stage of relation between two variables or more without any attempt to influence or manipulate those variable. (Faenkel and Wallen 2008:328). The presence of correlation and level of variable is important since by knowing the level of correlation, researcher may develop them suitable with the purpose of the research. The research is commonly involve statistics or level of relation that is called correlation (Mc Millan dan Schumacher, in Syamsuddin dan Vismaia, 2009:25). Correlational research uses an instrument to decide whether and in which level the relation between two variable or more may be quantitatified. According to Gay in Sukardi (2004:166) correlation research is one of ex-postfacto research since researcher is usually dismanipulate the variable existed and directly finding out the relation and level of variable that is reflected in correlation coefficient. Furthermore, Fraenkel and Wallen (2008:329) stated that correlation research is included in descriptive research since the research describe the recent condition in quantitative context that is reflected in variable. those correlation may detect scientific and statistically by correlational

Correlational reseaarch limited to the interpretation relation between variables and not to the casuality. The research may used for the next research such an experimtal research (Emzir, 2009:38). According to Sukardi (2004:166) correlation research has three kinds of important characteristics related to the researcher, they are : 1. Correlation research is right when the variables are complex and it is impossible to the researcher manipulate and control the variable as in experimental research. 2. It is possible that the variable may scaled intensively in the real setting. 3. It is possible that the researcher may discover significant association level. A. The purpose of Correlational Research The purpose of correlational research according to Suryabrata (in Abidin, 2010) is to detect how far the variations in certain factor relate to variations in one or more other factor based on correlation coefficient. Whereas according to Gay in Emzir (2009:38), correlational research is aimed to determine the relation among variables, or to make it as a prediction. Correlational study commonly seek some variables that is trusted to have a relation with certain major variable. B. The Characteristic of Correlational Research 1. The research is suitable if the variables are complicated or can not be researched by experimental method or can not be manipulated. 2. The research enable in measuring some variables and the relations in advanced for its real condition 3. The output of the research is a level or the high and low of relation and not the presence or absence of those relation. 4. The researh may predict certain variables based on independent variable. C. Fields of Correlational Study 1. Relation Study Relation research, relation or plain correlation may use to investigate the relation among the measurement result to two different variable at the same time. The research is aimed to determine the level or level of relation in a couple of variable or bivariate. Furthermore the

research is commonly become part of other research as a preliminary to other complex research. For example the multivaried correlation that investigate some variable relation simultaneously is always started by simple relation research to observe how those each variable is related to each other in pairs. In this plain correlation research, the relation among variable is indicated by the correlation coefficient value. The value of coefficient correlation is a statistics device to help researcher in understanding the level of relation. The coefficient value varied from -1,00 until +1,00 by certain statistics technique based on character from each data variable. Basically, the relation research design is quite plain, that is by collect two variable score from the same subject group and calculate the coefficient correlation. Hence in doing this research researcher must first determine a pair of variable to be investigated its level of relation. The sorting of both variable must be based on theory, asumption, previous research, or experience that both is possibly correlated. 2. Predictive Research

Predictive research is focussing in measuring one variable or more that is used to predict things in the future or other variable ((Borg & Gall dalam Abidin, 2010). The research involve correlation calculation among complex attitude, that is the predicted variable or criteria, and other variable that is predicted in correlated with the criteria or the predicator. The technique used to determine the level of prediction in both variable is regression analysis that produce regression coefficient value and is signed by R. The main difference between relational and predictive lies on the asumption of the variable relation researched. In relational research, researcher assume that the relation in both

variable is happening in two ways, in the other word, researcher just want to research whether or not the variables are correlated, without assuming that either variable emerge is earlier than the other. Thus, both variable are usually measured in the same time. In predictive research, other than investigating the relation between two variable, researcher is assuming that such variable may emerge earlier that the other, or one way relation. Hence both variable is measured in a series; the predictor variable is measured before the criteria variable emerge.

3. Multivaried Correlation A Technique to measure and investigate the level of relation among combination of three variables or more is called multivaried correlation technique. Multivaried correlation has some techniques and two of them are multiple regresion and canonical correlation. Multiple regression. Predicting a complex phenomena by only one factor like predictor variable is producing non accurate result. In certain things, the more information obtained the better of accuracy can be made, (Mc Millan & Schumaker in Abidin, 2010) by using two combination or more predictor variable, the prediction to criteria variable will be more accurate than using each variable independently. Hence the increasing of predictor will raise the accuration of criteria prediction. Canonical Correlation is an additional procedure for assessing the relationship between variables. Specifically, this analysis allows us to investigate the relationship between two sets of variables. For example, an educational researcher may want to compute the (simultaneous) relationship between three measures of scholastic ability with five measures of success in school. A sociologist may want to investigate the relationship between two predictors of social mobility based on interviews, with actual subsequent social mobility as measured by four different indicators. A medical researcher may want to study the relationship of various risk factors to the development of a group of symptoms. In all of these cases, the researcher is interested in the relationship between two sets of variables, and Canonical Correlation would be the appropriate method of analysis. D. Correlational Research Design Kinds of correlational research design according to Shaughnessy dan Zechmeinter are: 1. Bivariate correlation Bivariate correlation is a measure of the relationship between the two variables; it measures the strength of their relationship, which can range from absolute value 1 to 0. The stronger the relationship, the closer the value is to 1. The relationship can be positive or negative; in positive relationship, as one value increases, another value increases with it. In the negative relationship, as one value increases, the other one decreases.

2. Regression and Prediction When therre are correlation between two variable and we observe the score in one variable, the other score of variable may either be predicted. Regression refer to how well we may raise a prediction. As in coefficient correlation either -1,00 or +1,00, our prediction may raise better. 3. Multiple Regresion

Multiple regression identifies the best combination of predictors (IVs) of the dependent variable. Consequently it is used when there are several independent quantitative variables and one dependent quantitative variable (e.g., Which combination of risk taking behaviors [amount of alcohol use, drug use, sexual activity, and violenceIVs] best predicts the amount of suicide behavior [DV] among adolescents?). To produce the best combination of predictors of the dependent variable, a sequential multiple regression selects independent variables, one at a time, by their ability to account for the most variance in the dependent variable. As a variable is selected and entered into the group of predictors, the relationship between the group of predictors and the dependent variables is reassessed. When no more variables are left that explain a significant amount of variance in the dependent variable, then the regression model is complete. 4. Factor analysis

This statistic procedure identifies the presence of variable pattern. Most of the variable correlated and the presence of high correlation indicated that a factor is generally important. 5. Correlational design to draw a causal conclusion There are two design to make statement about cause and effect of using correlational method. They are path analysis design and cross-lagged panel design. path analysis design is used to determine which line connecting one variable to other variable whereas cross-lagged panel design is measuring two variables in both panel in advanced.

6.

System Analysis

The analysis system design involve complicated mathematics procedure to determine dynamic process as in simulatneous change, feedback loop, elements and relation trend. E. Main Design of Correlational Research Mainly the correlational research involve a correlation calculation among complex variable with other variable that is taken as predictor variable. According to Mc Milan and

Achumaker (2003) the stages cover problem determination, problem review or literary study, hypothesis, research design and research methodology, data collecting, data analysing and conclusion. 1. Problem Determination

Stated that problem in research is a gap between hopes and reality or the objectives that targetted by the researcher, nevertheless the target has not been reached. In preliminary action researcher must determine the problem of the research to be focussed on the study. The chacacteristic of researchable problem is having a contribution or advantage for some parties, is supported by empirical data and suitable with the ability and researcher desire (Sukardi, 2004:27-28). In correlational research, the chosen problem must have a valuable point in complex phenomenon attitude that needs an understanding. Despite, the variable involved in the research must consider certain things like theoritically, logically, and that the variable has certain relation. This may obtained by the previous research. 2. Problem review or Literary Review

After determining the problem, the important thing to do in research is literary review that will be base in obtaining theoritical base, framework and a temporary assumption determination thus researcher may see, allocating, organizing. The researcher may obtain the literary review from various sources like journal, reports, result of a research, science magazine, newspaper, relevant books, article, the conclusion of seminars or another sources.

3. Research Design or Research Method In this stage researcher determine the subject of the research and determine how to calculate the data. The subject involved in the research must be meausred in variables that become the research focus. The subject should be homogenous in external factors of variable that is investigated that may influence dependent variable. 4. Data collecting

Many various instrument is used to measure and collect data in each variable, in example questionnaire, tes, interview guiance, and observation guidance as theyre needed. The data collected by those instrument must be in numbers. In correlational research, variable

measuring is doing in the same time whereas in predictive research, predictor variable have to be measured a while before the criteria variable emerge to produce a meaningfull criteria prediction. 5. Data Analysis

Basically, the analysis in correlational research is done by dorrelating the resulat of one variable measurement with another result of variable measurement. In correlational research, bivariate correlation technique based on its data is used to calculate the level of relation among variables. Whereas in predictive, the technique use is regression analysis to determine the level of predictive ability of predictor variable to criteria variable. If there are only two variable a regular correlation analysis is used, if there are more than two variables multiple regression or canonical analysis is used. The result of the analsis is usually reported in coefficient correlation value or regression coefficient as well for the significance level and the variant proporsion of independent variable to dependent variable. The data interpretation in correlational research is when two variable correlated and resulted coefficient correlation with the (r) symbol. Those variable relation valued in -1 until +1. The value of (-) show a negative correlation in variables that is contradictory each other and the value of (+) show a positive correlation in variables that is approaching the same direction (Syamsudin and Vismaia 2009:25)

6.

Conclusion

The conclusion define about the result of descriptive analysis and discus about the matter researched in plain and brief sentence so that easily understood by the reader. F. Advantage and Disadvantage of Correlational Research The advantage of correlational research are : its ability to investigate the relation among variables simultaneously; and give the information of its level or strength of relation among variables researched (Abidin, 2010). Furthermore, the research is able to investigate some variables intensively and able to do prediction analysis without mass sample. The

disadvantage of the research are : the result is just to identify as the way it is and not showing any causalty relation; compare to experimental, the correlational is less strict rules since the minority of controlling independent variables; it oftenly used as short gun approach, that is to input data with no tight selection. (Abidin, 2010).

REFERENCES Abidin, Muhammad Zainal. 2008. Penelitian Korelasional. (artikel). Dalam

www.Muhammad Zainal Abidin Personal Blog.htm. di akses tanggal 25 September 2010. Atmodjo, J. Tri. 2005. Modul Penelitian Korelasi (artikel). Jakarta: Fikom Universitas Mercubuana Jakarta Emzir. 2009. Metodologi Penelitian Pendidikan Kualitatif dan Kuantitatif. Jakarta: PT Raja Grafindo Pergoda. Fraenkel, J.R dan Wellen, N.E. 2008. How to Design and Evaluate research in Education. New York: McGraw-Hill. McMilan, J dan Schumacher, S. 2003. Research in Education. New York: Longman. Nurgiantoro, Burhan. 2001. Penilaian dalam Pengajaran Bahasa dan Sastra edisi ketiga. Yogyakarta: BPFE-Yogyakarta. Ruseffendi. 1993. Statistika untuk Penelitian Pendidikan. Jakarta: Departemen Pendidikan dan Kebudayaan Direktorat Jenderal Perguruan Tinggi Proyek Pembinaan Tenaga Kependidikan Perguruan Tinggi. Sukardi. 2004. Metodologi Penelitian Pendidikan Kompetensi dan Praktiknya. Jakarta: Bumi Aksara. Syamsuddin dan Vismaia S. Damaianti. 2009. Metodologi Penelitian Pendidikan Bahasa. Bandung: PT Remaja Rosdakarya.

Anda mungkin juga menyukai