CORRELATIONAL RESEARCH
This paper fulfill the methodology research assignment
By
The second group
Kaharuddin
Hayaturradiah
Riska, s
Hastika
ENGLISH LITERATURE DEPARTMENT
ADAB FACULTY
ALAUDDIN STATE ISLAMIC UNIVERSITY OF MAKASSAR
2011
PREFACE
With the established system, the way to represent knowledge and learning is grades. Grades are everything for a student. But there are many factors that affect the grade of a student in a class: his abilities, his interest in the course, the teaching method, his peers, the classroom, even the schedule and many others. Some of these factors have a positive effect and others a negative one, resulting in higher or lower grades.
One of the negative factors is absences. The reasons why absences have a negative effect on grades are various. If a student is not present in class, something might be explained which the student won't understand later on, he/she could miss a homework or an assignment because he/she didn't know, or maybe the student will fall behind and have a hard time catching up with the rest of the class.
An investigation was conducted to try and find studies that had been done in this respect. Some studies were found establishing the relationship between absences and grades, but only one study was found regarding a correlation. It was a study done by Levine in child development courses under different assistance policies, and it found a negative correlation (Levine 1992). This negative correlation between absences and grades means that the more absences a student has, the lower his/her grade will be, and vice versa.
When gathering information, it was a surprise to find out that no such study had been conducted at the Instituto Tecnologico y de Estudios Superiores de Monterrey, Campus Querétaro, giving the research more value and making it even more interesting.
Written by
The second group
CONTENTS
Cover ................................................................................................................... i
Preface ............................................................................................................... ii
Contens .............................................................................................................. iii
CHAPTER I INTRODUCTION ................................................................................
A. Background ..................................................................................
B. Problem statement ......................................................................
C. Advantages ..................................................................................
CHAPTER II CONTENTS .......................................................................................
A. Correlational research: defenition and purpose ..........................
B. The correlational research process .............................................
C. Relationship studies ....................................................................
D. Prediction studies ........................................................................
E. Other correlation-based analyses ...............................................
F. Problem to consider in interpretting correlation coefficient .....
G. An example of the correlational research ..................................
CHAPTER III CLOSING .......................................................................................
BIBLIOGRAPHY ................................................................................................
CHAPTER I
INTRODUCTION
A. Background
Some forms and how the technic to write research were found. The form of broad can be different, but soul and reasonable were same. Basically not only how to the technic to write a research but also understand about the original basic. Fulfill these forms and technic writing were appetite and preference someone inspite of institute who have attentioned to the variable, such as what were researched who were the reader and where they were going to presentate the report of the rsesearch.
With the established system, the way to represent knowledge and learning is grades. Grades are everything for a student. But there are many factors that affect the grade of a student in a class: his abilities, his interest in the course, the teaching method, his peers, the classroom, even the schedule and many others. Some of these factors have a positive effect and others a negative one, resulting in higher or lower grades.
An investigation was conducted to try and find studies that had been done in this respect. Some studies were found establishing the relationship between absences and grades, but only one study was found regarding a correlation. It was a study done by Levine in child development courses under different assistance policies, and it found a negative correlation (Levine 1992). This negative correlation between absences and grades means that the more absences a student has, the lower his/her grade will be, and vice versa.
When gathering information, it was a surprise to find out that no such study had been conducted at the Instituto Tecnologico y de Estudios Superiores de Monterrey, Campus Querétaro, giving the research more value and making it even more interesting.
B. Problem statement
From this paper we can make question that are:
1. What is the defenition of correlational research?
2. What are the correlational research process?
3. How we make an example about the correlational reasearch?
C. Advantages
Some advantages study about correlational research:
1. We can understand and use the correlational research for researching.
2. Know about the correlational process.
3. We can differ among the methodology research
CHAPTER II
CONTENT
A. Correlational research: definition and purpose
Correlational research is sometimes treated as a type of descriptive research, primarly because it does describe an existing condition. However, the condition it describes is distictly deifferent from the conditions typically described in survey or observational studies. The degree of relationship isexpressed as a correlation coefficient. If a relationship exist between two variables, it means that scores within a certain range on one variable are associated with score within a certain range on the other variable. For example, there is a relationship between intelligence and academic achievement; persons who get high scores on intelligence test tend to have high grade point averages, and persons who get low scores on intelligence test tend to have low grade point averange.
The purpose of correlational study may be to determine relationships between variables (relationship studies) or to use these relationships to make predictions(prediction studies). Prediction study typically investigate a number of variables believed to be related to a major, complex variable, such as achievement. Variables found not to be highly related to achievement will be dropped from further examination, whereas variables that are highly related to achievement may be examined in causal comparative or experimental studies to determine the nature of the relationships.
In general, a correlational study is a quantitative method of research in which you have 2 or more quantitative variables from the same group of subjects, & you 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).
B. The correlational research process
Although relationship and pridiction studies have unique features that differentiate them, their basic process are very similar.
problem selection
correlational studies may be designed either to determine whether and how a set of variable are related or to test hypoteses regarding expected relationships. Variable to be correlated should be selected on the basis of some rationale. That is, the relationship to be investigated should be a logical one, suggested by theory or derived from experience. Having a theoritical or experiential basis for selecting variables to be correlated makes interpretation of result more meaningful correlational”treasure hunts” in which the researcher correlates all sorts of variables to see “what’s turn up” are strongly dis couraged. This research strategy (appropriately referred to as a “shotgun”or “fishing” approach) is very ineffecient and makes findings difficult to interpret.
Participant and instrument selection
The sample for a correlational study is selected by using an acceptable sampling method, and 30 participant are generally considered to be minimally acceptable sample size. Thus, care must be taken so select measures taht are valid and reliable for your purposes.
Design and procedure
The basic correlation research design is not complicated; scors for two (or more) variables or interest are more obtained for each member of the sample, and the paired scores are then correalated. The result is expressed as a correlation coeficient that indicates the degree of relationship between the two variables. Some studies investigate more than two variables, and some utilize complex statistical procedures, but the basic design is similar in all correlational studies.
Data analysis and interpretation
When two variable are correlated, the result is a correlated coefficient, which is a dicimal number ranging from -1.00 to +1.00. The correlation coeffient indecates the size and direction of the relationship between variables. A coefficient near +1.00 has a high size (it represents a high degree of relationship) and positive direction. This means that a person with a high score on one of the variable is likely to have a low score on the other. An increase one variable is assosiated with an increase on the other variable. If the coefficient is near .00, the variable are not related. This means that a person’s score on one variable provides no indication of what the person’s score is on the other variable.
C. Relationship study
The strategy of attempting to understand a complex variable such as self-concept by identifying variables correlated with it has been more succesful for some variables than do others. For example, whereas a number of variables correlated with achievement have been identified, factors significantly related to succes in such areas as administrationand teaching have not been as easy to pin down. Relationship studies that have not uncovered useful relationships have nevertheless identified variables that can be excluded from future studies, a necessary step in science.
Data collection
In a relationship study, the researcher first identifies the variables to be correlated. For example, if you were interested in factors related to self-concept, if you might identify the variables introversion academic achievement, and sociocconomic status. As noted previously, you should have a reason for selecting variables and the study. A shotgun approach is inefficient and often misleading. Also, the more correlation coefficientthat are computed at one time, the more likely is that some wrong conclusions about the existence of a relationship will be reached. Computing only 10 or 15 correlation coefficients generally doesn’t cause a problem. Computing 100 coffecients, on the other hand, greatly increases the chance for error. Thus, a smaller number of carefully selected variables is much preffered to a larger number of carelessly selected variables. After identifying variables, the next step in data collection is identifying an apprppriate population of participants from which to select a sample.
Data analysis and interpretation
In a relationship study, the scores for one variable are correlated with the scores for another variable. If a number of variable are to be correlated with some particular variable of primary interest, each of the variables would be correlated with that variable; each correlation coefficient then represents the relationship between a particular variable and the variable primary interest. The end result of data analysis is a number of correlation coefficient, ranging between -1.00 and +1.00. There are a number of different methodes of computing correlation coeffecient.
Most correlational techniques are based on the assumption that the relationship being investigated is a liniear relationship, one in which an increase (or decrease) in one variable is assosiated with a corresponding increase(or decrease) in another variable. Plotting the scores of two variables that have a linear relationship results in a straight line, if a relationship is perfect (+1.00 or -1.00), the line will be perfectly straight, but if there is no relationship, the points will form a scattered, random plot.
D. Prediction studies
If two variables are highly related, scores on one variable can be used to predict scores on the other variable. High school grades, for example, can e used to predict college grades. Or scores on a teacher certification exam can be used to predict prinsipals’ evaluation of teachers’ classroom performance. The variable used to predict (high school grades or princioal evaluations) is a complex variable called the criterion. A prediction study is an attempt to determine which of a number of variable are most highly related to the criterion variable.
More than one variable can be used to make predictions. If several predictor variables each correlate well with a criterion, then a prediction based on combination of those variables will be more accurate than a prediction based on one of them. For example, a prediction of probable level of GPA succes in college based on high school grades will be less predicative than a prediction based on high school grade, rank in graduating class, and scores on college entrance exams. Although there are several major differences between prediction studies and relationship studies, both involve determining the relationship among a number of identified variables.
Data collection
As in all correlation studies research participant must be able to provide the desired data and be available to the researcher. Valid measuring instruments should be selected to represent the variables. It is especialy important that the measure used as the criterion variable be valid. If the criterion were”succes on the job,” the researcher would have to carefully define”success”in quantifiable terms in order to carry out the prediction study. For example, size desk would probably not be a valid measure of job success (although you never know), whereas number of promotions or salary increases probably would be. The major difference in data collection procedure for a relationship study and a prediction study is that in a relationship study all variable are collected within a relatively short period of time, whereas in a pridiction study the predictor variable are generally obtained earlier than the criterion variable.
Once the strenght opf the predictor variable is established, the predictive relationship is tested on a new group of participants to determine how well it will predict for other groups. An interesting characteristic of pridiction studies is shringkage, the tendency of a prediction equation (discussed shortly) to become less acurate when used with a group other than the one on which the equation was originally developed.
Data analysis and interpretation
In a relationship study, each predictor variable in a prediction study is correlated with the criterion variable. Data analysis in prediction studies differ somewhat from that of relationship studies, however. It is beyond the scope of this text to discuss the statistical processes related to the analysis of prediction studies. For a single variable prediction, the form of the variable prediction, the form of the prediction equation is
Y= ɑ + bX
Where:
Y= the predicted criterion score for an individual
X= an individual’s score on the predictor variable
ɑ= a constant calculated from the score of all participants
b=a coefficient that indicates the constribution of the predictor variable to the criterion variable.
Suppose, for example, that we wished to predict a students’s college GPA using hill school GPA. We know that the student high school grade average is 3.0, the coefficient .87, and the constant ɑ is .15. the student’s predicted score would be calculated as a follows
Y= .15 + .87 (3.0) = .15 + 2.61 = 2.76 predicted college GPA
We can compare the student’s predicted college GPA to the student’s actual college GPA it some subsequent time to determine how accurate the prediction equation is.
E. Other correlation-based analyses
Many sophicticated statistical analyses are based on correlational data. We will briefly describe a number of these., recognizing that they are statically complex. Descriminant fuction analysis is quite similar to multiple regression analysis, with one major difference: the criterion variable is categorical, not continuous. In multiple regression, continuous predictor variables are used to predict a continuous crityerion variable. In discriminant fuction analysis, continuous predictor variable are used to predict a categorical variable, such as introverted/extroverted, high anxiety/low anxiety, or achiever/nonachiever. Thus, the prediction made are about categoriacal group membership.
Path analysis allow us to see the relationships and patterns among a number of variables. The outcome of a path anlysis is a diagram that shows how variable are related to one another. Suppose, for example, that we wanted to examine the connection (paths) between variable X and variable A,B, and C. This approach provides more theoritical validity and statistical precision in model diagrams it produce than those of path analysis. Like path analysis, it clarifies the direct and indirect interrelationship among variable relative to a given variable.
Trying to make sense of a large number of variable is difficult, simply because there are so many variables to be considered. Factor analysis is a way to take a large number of variables
A
C D
B
And group them into smaller number of cluters called factors. Factor analysis computing correlations among all the variables and then derives factors by finding groups of variable are correlated highly among each other, but lowly with each other variables. The factors not the many individual items within the factor, are then used as variables. Factor produces a manageble number of factor variables to deal with and analyze.
F. Problem to consider in interpreting correlation coeficients
The quality of the information provided in correlation coeficient depends on the data are calculated from. It is important to ask the following questons when interpreting correlation coefficients:
• Was the proper correlation method used to calculate the correlation?
• Do the variable being correlated have high reliabilities?
• Is the validity of the variables strong?
• Is the range of scores to be correlated restricted or extended?
• How large is the sample size?
G. Example of the correlational research process
From this paper we take an example thesis which is using the correlational research. We can know the differential process of the some researches.
Name: Mardiana
The thesis tittle: THE CORRELATION BETWEEN THE STUDENTS READING COMPREHENSION ACHIEVEMENT AND THEIR ATTITUDES TOWARDS ENGLISH
Problem statement:
In relation to the background describe earlier, the writer formulates some research questions as follows.
1. What is the students’ attitude toward English?
2. Is there a signifiacnt correlation between the reading comprehension achievement of the fifth semester students, academic year 2001/2002 of the English Department of UNM makassar and their attitude towards English.
Hypotesis:
Based on the problem statement above, the writer proposed a hypotesis;
There is a significant correlational between the reading comprehension achievement of the fifth semester students of English department of UNM makassar and their attitude towards English.
Instrument of the research:
In this research, the writer utilized two kinds of instruments namely:
1. Multiple choice test
2. Questionnaire
Population and sample:
• The population
The population of the research consisted of the third year students namely the fifth semester students(S1 Program) of English Education Department OF UNM Makassar. Academic year 2001/2002
The reason why the third year students were taken is that they had learned English for more than eight years.
The result of learning for eight years could fairly be describe how far the students achievement in reading comprehension and their attitude in English and the correlation between both.
• Sample
In this research, the writer used total sampling. All of the students of S1 program were taken as the sample because there were not many students at that semester.
The writer hopes that by using total sampling, this research will be more accurate.
CHAPTER III
CLOSING
Correlational research is a quantitative method of research which aims to determine if there exists any kind of relationship between two variables. Correlational research is an easy way to understand how two or more groups are related to each other. For example, a correlational study on cigarette smoking can examine the relationship between cigarette smoking and lung cancer. The correlational research method is purely observational in nature and the researcher merely examines the variables without any kind of manipulation. Correlational research is not to be confused with the cross sectional research as the nature and the scope of both these studies is entirely different.
CONCLUSION
1. The research successfully found the exact correlation coefficient between grades and absences for the ITESM, Campus Querétaro, being -.44.
2. It also discovered differences between the careers on the campus, finding that some had a positive correlation (Maestria 0.17).
3. Finally, it gathered the opinion of the students and determined that half knew of this correlation but that it didn't affect their grades.
In future studies it could be important to determine how much the assistance (attendance) policies affect the correlation between grades and absences. To accomplish this, the research could be done in other colleges and universities with different policies. Maybe it would be possible to find, if there was no assistance required, how that would affect the relationship between grades and absences.
BIBLIOGRAPHY
Downess, W. Language and society. London: fontana. 1984
Mardiana. 2002. The correlation between the students reading comprehension achievement and their attitudes towards English. Makassar: Fakultas Tarbiyah IAIN Alauddin.
Gay, L.R. 2006. Educational research: competence for analysis applications 8th edition. Columbus: pearson merrill prentice hall.
http://www.buzzle.com/articles/correlational-research.html
