CORRELATION-RANK DIFFERENCE METHOD

CORRELATION-RANK DIFFERENCE METHOD

Introduction

            Correlation is the statistical method whereby relationship is expressed on a quantitative scale. The degree of correlation is expressed in figures ranging from 0 to 1 and 0 to -1.

Definitions

            According to English and English:-

                        “Correlation is a relationship or dependence. It is the fact that two things or variables are so related that change in one is accompanied by a corresponding or parallel change in the other”.

            According to Ferguson:-

                        “Correlation is concerned with describing the degree of relation between two variables”.

            According to Lathrap:

                        “Correlation is a joint relationship between two variables”.

Types of correlation

1. Positive correlation

     If the weight of an individual increases in proportion to increase in his height, the relation between this increase of height and weight is called as positive correlation.

2. Negative correlation

It is just the opposite of positive correlation. If the weight of an individual does not increase in proportion to increase in his height or if the weight of an individual decreases with an increase in height, then it is said to be negative correlation, also ranges from 0 to -1. -1 is perfect negative correlation.

3. Zero correlation

Zero correlation is a correlation showing no relationship, or a correlation having a correlation coefficient of zero.

Method of finding out the correlation

            Various persons have suggested various methods for finding out correlation. Two methods that are prevalent and important are:-

1.      Rank Order Method.

2.      Product Moment method

Rank Order Method

            Differences among individuals in many traits can often be expressed by ranking the subjects 1-2-3 order when such differences cannot be measured directly. For instance, individuals may be ranked in order of merit for obedience. Industriousness punctuality, honesty, salesmanship or social adjustment. Similarity various advertisements colour combination, jokes and picture which are difficult to evaluate numerically may be put in order of merit for beauty, humour, artistic quality or some other quality.

            The formula for calculating the correlation by Rank order method is as under:

                     6SD²

r(rho)=1- ________

                    N(N²-1)

r(rho) stands for coefficient of correlation form rank differences.

SD² represents the sum of the squares of differences in rank. N represents number of pairs.

In order to illustrate this formula, we give below an example:-

Student	Marks of Eng	Marks of Math	R1	R2	d	d2
A B C D E	22 18 19 15 17	18 15 17 16 19	1 3 2 5 4	2 5 3 4 1	1 2 1 1 3	1 4 1 1 9
N=5						SD2 =16

                     6SD²

r(rho)=1- ________

                    N(N²-1)

                      6 x 16

          =1- ________

                    5(25-1)

                     96

          =1- ________

                   120

             =1-.8

         = .2

Interpretation Table

S.No	Degree of correlation	Types of correlation
1 2 3 4 5 6	±.00 to ±.20 ±.20 to ±.40 ±.40 to ±.70 ±.70 to ±.90 ±.90 to ±1.00             ±1.00	Negligible Low Moderate High Very high Perfect

So we can interpret result. 2 by saying that there is negligible positive correlation.

Uses of the co-efficient of correlation

            The use of coefficient of correlation is used quiet profitably in prediction. In almost all social sciences this is now being increasingly used. It is useful whenever each number of a group of individuals has been measured on two or more traits. It expresses at one figure the average degree of  resemblance etc., between the two traits. Its specific uses may be given as follows

1.            Prognosis (Prediction)

The co-efficient of correlation is used quite profitably in prediction. In a number of studies it is used to predict the success one will achieve in his further educational careers.

2.            Reliability

The co-efficient of correlation has been used very often to test the reliability. Through calculation of this statistics it has been sought to be asserted whether or not a test measures on two successive occasions the same type of thing.

3.            Validity

A test’s width value can be obtained through correlation. When ever a test is constructed the tests, not what it claims to test. This question is answered by the magnitudes of the coefficient with various criteria.

4.            Test Construction

The coefficient of correlation is also being used in the test construction. Whenever a new test is constructed, there are always the questions of whether each element of the test is related to mother elements are to the test as a whole and as to whether each element is related to the criterion chosen. Those relationships are all examined through the technique of correlation.

Importance of Correlation

            Correlation is very important in the field of psychology and education as a measure of relationship between test scores and other measures of performance. With the help of correlation, it is possible to have a correct idea of the working capacity of the person. With the help of it, it is also possible to have knowledge of the various qualities of an individual. After finding the correlation between the two qualities or different qualities of an individual, it is also possible to provide his vocational guidance. In order to provide educational guidance to a student in selection of his subjects of study, correlation is also helpful and necessary.