Correlation enquiry is a study to determine the human relationship as well as the flat of association betwixt ii variables or to a greater extent than without whatever endeavor to influence these variables hence that at that topographic point is no manipulation of variables (Faenkel as well as Wallen, 2008: 328). The beingness of a human relationship as well as the flat of this variable is of import because past times knowing the flat of the existing relationship, researchers volition move able to railroad train inward accordance alongside the role of research. This type of enquiry unremarkably involves statistical size / flat of human relationship called correlation (Mc Millan as well as Schumacher, inward Shamsuddin as well as Vismaia, 2009: 25). Correlation enquiry using instruments to determine whether, as well as to what extent, at that topographic point is a human relationship betwixt ii or to a greater extent than variables that tin move quantified.
According to Gay inward Sukardi (2004: 166) correlation study is i business office of the ex-post facto enquiry because researchers unremarkably practise non manipulate the nation of a given variable as well as straight search for the beingness of a human relationship as well as the flat of variable relationships are reflected inward the correlation coefficient. Furthermore, Fraenkel as well as Wallen (2008: 329) mentions the correlation enquiry into the study because it represents a description of the concern depict atmospheric condition that accept occurred. In this study, researchers sought to depict the electrical flow atmospheric condition inward the context of quantitative reflected inward the variable.
Correlation enquiry conducted inward diverse fields including education, social, as well as economic. This study is limited to the interpretation of the relationship between variables was non up on causality, but this enquiry tin move used every bit a reference for time to come enquiry every bit experimental enquiry (Emzir, 2009: 38). According to Sukardi (2004: 166) correlation study has 3 of import characteristics for researchers who desire to occupation it. Three characteristics are every bit follows. Appropriate if the correlation study of complex variables as well as researchers impossible to manipulate as well as command variables every bit inward the experimental study. Allows intensively measured variables inward the setting (environment) real. Allows researchers to acquire a important score of association.
- Appropriate if the correlation study of complex variables as well as researchers impossible to manipulate as well as command variables every bit inward the experimental study.
- Allows intensively measured variables inward the setting (environment) real.
- Allows researchers to acquire a important score of association.
Correlational Research Objectives
Correlational enquiry purposes based on Suryabrata (in Abidin, 2010) is to respect the extent to which variations inward the factors associated alongside variations inward i or to a greater extent than other factors based on the correlation coefficient. Meanwhile, according to the Emzir Gay (2009: 38) The role of a correlational study was to determine the human relationship betwixt variables, or to occupation these relationships to brand predictions. Studies investigating the human relationship is unremarkably a number of variables that reliably associated alongside a major variables, such every bit learning outcome variables did non accept a high correlation eliminated from farther attention.
The Characteristics of Correlational Research
Here are the characteristics of Correlation research:
- This variety of enquiry is suitable done when the variables studied complex as well as / or tin non move investigated past times experimental methods or tin non move manipulated.
- This variety of study allows the measuring of multiple variables simultaneously as well as mutual relation inward realistic circumstances.
- The output of this enquiry is high-level or depression flat of mutual relations as well as non the presence or absence of such a human relationship to each other.
- Can move used to predict sure as shooting variables based on the independent variable.
Kinds of Correlational Research
This next explanation is virtually kinds of correlation research, hither are:
1. Research Relation
Research relations, relational, or uncomplicated correlation (often simply called correlation only) is used to investigate the human relationship betwixt the results of measurements on ii different variables at the same time. This study aims to determine the flat or score of human relationship betwixt a span of variables (bivariate). Furthermore, studies of this variety are oftentimes business office of about other study, conducted every bit a prelude to other studies of complex processes. For example, inward a multivariate correlation studies examining the human relationship several variables simultaneously inward full general ever begins alongside a uncomplicated human relationship of enquiry to run across how each of these variables relate to each other inward pairs.
In this uncomplicated correlation study the human relationship betwixt these variables is indicated past times the value of the correlation coefficient. The value of the correlation coefficient is a statistical tool used to assistance researchers inward agreement the human relationship level. Coefficient values varied from -1.00 to +1.00 obtained using sure as shooting statistical techniques appropriate to the graphic symbol of the information of each variable.
Basically, the pattern of the study of this human relationship is quite simple, as well as alone had to collect a score of ii variables of the same grouping of subjects as well as and then calculate the correlation coefficient. Therefore, inward this research, the researcher maiden of all span of variables that volition determine the flat of human relationship investigated. The choice of these ii variables should move based on the theory, assumptions, the results of enquiry that preceded, or sense that both are likely related.
2. Predictive Research
In the implementation inward the plain of education, many situations that require doing prediction or forecasting. At the maiden of all of the novel academic year, for example, every schoolhouse because of limited facilities, oftentimes accept to conduct the applicants who volition move admitted to prospective students.
This variety of correlation study focuses on the measuring of i or to a greater extent than variables that tin move used to predict or predict events inward the time to come or other variables (Borg & Gall inward Abidin, 2010). This study every bit relational research, involving the calculation of correlation betwixt a complex pattern of behavior, namely the variable target prediction or forecast of events (called criteria), as well as other variables idea to move related to the criteria, the variables used to predict (called predictor ). The technique used to determine the flat of prediction betwixt the ii variables is a regression analysis technique that produces the regression coefficient, which is denoted past times R.
The principal differences betwixt relational as well as enquiry studies of this variety lies inward the assumptions underlying the human relationship betwixt the variables studied. In a relational study, researchers assume that the human relationship betwixt the ii variables plough over inward both directions, or inward other words, he simply wanted to investigate whether the ii variables accept a relationship, without the supposition that the variables that accept appeared before than others. Therefore, the ii variables are unremarkably measured at the same time. Being inward predictive studies, inward add-on to desire to investigate the human relationship betwixt ii variables, researchers also accept the notion that i of the variables appearing ahead of the other, or one-way relationship. Therefore, dissimilar relational research, both variables are measured inward fourth dimension sequence, the predictor variables were measured before going on measure variables, as well as tin non move otherwise.
3. Correlation Multivariate
Techniques to mensurate as well as investigate the score of human relationship betwixt the combination of 3 or to a greater extent than variables called multivariate correlation techniques. There are several techniques that tin move used, ii of which volition move discussed hither are: double or multiple regression regression as well as canonical correlation.
Multiple regression. Predicting a complex phenomenon alongside alone i factor (predictor variables) oftentimes alone give less accurate results. In many ways, the to a greater extent than information is obtained to a greater extent than accurate predictions tin move made (Mc Millan & Schumaker inward Abidin, 2010), past times using a combination of ii or to a greater extent than predictor variables, prediction of the measure variable volition move to a greater extent than accurate than simply using each predictor variables individually. Thus, increasing the number of predictors volition growth the prediction accuracy criteria.
Canonical correlation. Basically this same technique alongside multiple regression, where multiple variables combined to predict the measure variable. However, dissimilar the multiple regression involving alone i measure variable, canonical correlation involves to a greater extent than than i measure variable. This correlation is useful to answer the question, how a laid of predictor variables predicting the measure variable series? Thus, canonical correlation tin move regarded every bit an extension of multiple regression, as well as vice versa, multiple regression tin move considered every bit business office of the canonical correlation (Pedhazur inward Abidin, 2010). This correlation is oftentimes used inward exploratory enquiry that aims to determine whether the number of variables accept a human relationship alongside each other are similar or different.
Correlational enquiry has diverse types of design. Shaughnessy as well as Zechmeister (in Emzir, 2009: 48-51), namely:
1. Bivariate Correlation
Bivariate correlation study pattern is a pattern study aimed to depict the human relationship betwixt ii variables. The human relationship betwixt the ii variables are measured. The human relationship has a score as well as direction. Level relationships (how rigid the relationship) is unremarkably expressed inward number betwixt -1.00 as well as +1.00, which is called the correlation coefficient. Correlation null (0) indicates no relationship. Moving correlation coefficient of -1.00 or +1.00 direction, a perfect correlation inward the ii extremes (Emzir, 2009: 48). Direction of the human relationship is indicated olh symbol “-” as well as “+”. Influenza A virus subtype H5N1 negative correlation agency that the higher the score on a variable, the lower the score on the other variable or vice versa. The positive correlation indicates that the higher the score on a variable, the higher the scores on about other variable or vice versa (Emzir, 2009: 48).
2. Regression as well as Prediction
If at that topographic point is a correlation betwixt the ii variables as well as nosotros know the score on i variable, scores on both variables tin move predicted. Regression refers to how good nosotros tin brand this prediction. As proficient correlation coefficient approach -1.00 or +1.00, nosotros tin amend predictions.
3. Multiple Regression (Multiple Regression)
Multiple regression is a uncomplicated extension of regression as well as prediction alongside the add-on of several variables. The combination of these variables gives to a greater extent than mightiness to us to brand accurate predictions. What nosotros predicted called variable criteria (criterion variable). What nosotros occupation to brand predictions, the variables that are already known is called the predictor variable (predictor variables).
4. Factor Analysis
This statistical physical care for identifies existing variable pattern. Influenza A virus subtype H5N1 large number of correlated variables as well as a high correlation betwixt the presence indicates an of import factor that is common.
5. Correlation pattern used to clit causal inferences
There are ii designs that tin move used to brand statements virtually the causes as well as consequences of using the correlation method. The pattern is the pattern of path analysis (path analysis design) as well as cross-end panel pattern (cross-lagged panel design). Path analysis is used to determine which of a number of paths that connect i variable to about other variable. While the pattern of the terminal cross panel measuring ii variables at ii points simultaneously.
6. Analysis organisation (System Analysis)
This pattern involves the occupation of complex mathematical procedures / complicated to determine the dynamic processes, such every bit changes over time, every bit good every bit the feedback chemical component meshes as well as flow relationships.
Basic Design Correlation Design
Basically, correlation studies involving the calculation of the correlation betwixt the complex variables (variable criteria) alongside other variables that are considered every bit bonafit human relationship (predictor variables). Measures proficiency flat this study are to a greater extent than oftentimes than non inward Mc Milan as well as Schumaker (2003), namely the decision of the issues, problems or literature review, enquiry enquiry or hypothesis, enquiry pattern as well as methodology of the study, information collection, as well as information analysis, conclusion.
1. Formulating the Problem
Dewey (in Shamsuddin as well as Vismaia, 2009: 42) states the job inward enquiry is a gap betwixt what is expected past times the fact that at that topographic point is or something that made the targets laid past times the researchers, but the target is non reached. In each study the maiden of all stride to practise enquiry is to determine the enquiry problems that volition move the focus of his studies. The characteristics of the job worth studying is that tin move researched (researchable), accept contributed or kebermanafaatan for many parties, tin move supported past times empirical information as well as the corresponding mightiness as well as willingness of researchers (Sukardi, 2004: 27-28). In a correlational study, issues selected should accept important value inward the demeanour pattern of a complex phenomenon that requires an understanding. In addition, the variables included inward the study should move based on consideration, both theoretically as well as reason, that these variables accept a sure as shooting relationship. This tin unremarkably move obtained based on the results of previous studies.
2. Influenza A virus subtype H5N1 review of job or Library Studies
After determining the problem, an of import enquiry action is the study of literature that became the foundation for obtaining the basic theory, framework as well as decision of provisional estimates hence that researchers tin understand, allocate, organize, as well as occupation the variation inward the library field. Various sources to obtain the theories related to the job nether study is of journals, enquiry reports, scientific magazines, newspapers, books relevant, results of seminars, scientific articles as well as sources.
3. Research Methodology
The study pattern or At this phase the researchers determined that the enquiry subjects volition move selected as well as determine how the information processing. Subjects were recruited for this study must move measured inward the variables that are the focus of research. The subjects to move relatively homogeneous inward factors exterior the studied variables that may touching on the dependent variable. When the subjects involved accept important differences inward these factors, the correlation betwixt the variables studied are becoming blurred. To cut down the heterogeneity, the researcher tin class subjects into groups based on the flat of sure as shooting factors as well as and then examine the human relationship betwixt the study variables for each group.
4. Data collection
Various types of instruments tin move used to mensurate as well as collect information of each variable, such every bit questionnaires, tests, interview guidelines as well as guidelines for observation, of course, tailored to the needs. Data collected past times these instruments should move inward the cast of numbers. In a correlational study, the measuring variables tin move done inward a relatively equal. Being inward predictive studies, the predictor variables should move measured over a flow of fourth dimension before the measure variable occurs. If not, as well as then a prediction of these criteria is meaningless.
5. Analysis of the data
Basically, the analysis inward a correlational study done past times correlating the results of measuring of a variable alongside about other variable measuring results. In a correlational study, bivariate correlation technique, according to the type of data, used to calculate the score of human relationship betwixt variables alongside i another. Being inward a predictive study, the technique used is the regression analysis to determine the flat of predictive capability predictor variable to variable criteria. However, it tin also move used when the normal correlation analysis involves alone ii variables. When involving to a greater extent than than ii variables, for example, to determine whether ii or to a greater extent than predictor variables tin move used to predict the measure variable is amend than when used individually, multiple regression analysis techniques, multiple regression or canonical analysis tin move used. The results of this analysis are unremarkably reported inward price of the coefficient of correlation or regression coefficients as well as significance levels, inward add-on to the proportion of variance contributed past times the independent variable on the dependent variable. Interpretation of the information inward a correlational study is when connecting the ii variables volition make correlation coefficient alongside the symbol (r). The human relationship of these variables declared alongside the value of -1 till +1. Value (-) indicates negative correlation conflicting variables as well as values (+) indicates a positive correlation approach each other variables inward the same management (Syamsudin as well as Vismaia, 2009: 25).
It contains the results of the analysis of the description as well as give-and-take of the enquiry past times using easily understood reader briefly.
Abidin, Muhammad Zainal. 2008. Penelitian Korelasional. (artikel). Dalam http://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 DKI 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 as well as Evaluate enquiry inward Education. New York: McGraw-Hill.
McMilan, J dan Schumacher, S. 2003. Research inward 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.