RANK CORRELATION

Spearman’s rank correlation coefficient is defined as:

R 1
6  D2 (OR) R  1
6  D2
N ( N 2  1) N3  N

1.The ranking of 10 students in two subjects A and B are as follows

A 6 5 3 10 2 4 9 7 8 1
B 3 8 4 9 1 6 10 7 5 2
Find the spearman’s rank correlation coefficient.

R1 R2 (R1-R2)2=D2
6 3 9
5 8 9
3 4 1
10 9 1
2 1 1
4 6 4
9 10 1
7 7 0
8 5 9
1 2 1
 D 2  36

R 1
6 D2  1  6  36
1
216
 0.782
N3  N 103  10 990

2. Practice problem:

Find Spearman’s rank correlation coefficient.

X 1 6 5 10 3 2 4 9 7 8
Y 3 5 8 4 7 10 2 1 6 9
Z 6 4 9 8 1 2 3 10 5 7

Dr.K.KAVITHA
3. Calculate spearman’s coefficient of rank correlation for the following:

X 53 98 95 81 75 61 59 55
Y 47 25 32 37 30 40 39 45

X Y Rank X Rank Y R1-R2=D D2

(R1) (R2)
53 47 8 1 7 49
98 25 1 8 -7 49
95 32 2 6 -4 16
81 37 3 5 -2 4
75 30 4 7 -3 9
61 40 5 3 2 4
59 39 6 4 2 4
55 45 7 2 5 25
 D 2  160
R  1
D2  1  6 160  1 1.9048  0.905
6
N3  N 83  8

4. From the following data of the ranks obtained by 8 students in the computer
science and statistics papers, Compute rank correlation coefficient.

Marks in 15 20 28 12 40 60 20 80
computer
science
Marks in 40 30 50 30 20 10 30 60
statistics

Marks in Marks in RankX RankY D=R1-R2 D2

computer statistics(Y) (R1) (R2)
science(X)
15 40 7 3 4 16
20 30 5.5 5 0.5 0.25
28 50 4 2 2 4
12 30 8 5 3 9
40 20 3 7 -4 16
60 10 2 8 -6 36
20 30 5.5 5 0.5 0.25
80 60 1 1 0 0
  D 2  81.5

R  1
6D2  0.0298
N3  N

Regression lines(or)Linear Regression

The equation of the line of regression of X on Y is given by

 x
(X  x)  r (Y  y )
 y

and the equation of line of regression of Y on X is given by

 y
(Y  y )  r (X  x)
 x

Where ‘r’ is the correlation coefficient between X and Y.  x and  y

represents the standard deviation of X and Y respectively.

   y 
The quantities    and    are called regression coefficients. The
r  x  r

 y   x 

product of regression coefficients is equal to r 2 .

Problems:

1. Find the mean values of the variables X and Y and correlation

coefficient from the following regression equations.
2Y  X  50 .......... .(1)
3Y  2 X  10 .......... .( 2 )

Solve the equations (1) and (2)

X=130= X ;Y=90= Y

Dr.K.KAVITHA
 Rewriting (1) and (2) as

1 y
Y  X  25; [(Y  Y )  r (X  X )
2 x
3 
X  Y  5; [(X  X )  r x (Y  Y )
2 y

y 
r  1/ 2; r x  3/ 2
x y

3
r2   r  0.866
4

2. The correlation coefficient between two random variables X and Y is

r=0.6 if  x  1.5,  y  2, X  10; and Y  20. Find the regression lines of
(i)Y on X and (ii)X on Y.

x 
Regression lines of X on Y is ( X  x )  r  (Y  y )
y

1.5
( X 10)  0.6( )(Y  20)  X  0.45Y  1
2

 y
Regression lines of Y on X is ( Y  y )  r (X  x)
x

2
(Y  20)  0.6( )( X 10)  Y  0.8X  12
1.5

3. From the following data , obtain two regression equations

X 6 2 10 4 8
Y 9 11 5 8 7

Dr.K.KAVITHA
 X xX x x2 Y yY  y y2 xy

6 0 0 9 1 1 0
2 -4 16 11 3 9 -12
10 +4 16 5 -3 9 -12
4 -2 4 8 0 0 0
8 +2 4 7 -1 1 -2
 X  30 x  0  x 2  40 Y  40 y  0  y 2  20  xy  26

x
X  6  2 10  4  8  30  6
N 5 5

y
Y 40
 8
N 5
The equation of the line of regression of X on Y is given by

x
(X  x)  r (Y  y )
 y


r x 
 xy   26  1.3
y
 y 2 20

 X  6  1.3(Y  8)  X  16.4  1.3Y

The equation of line of regression of Y on X is given by

y
(Y  y )  r (X  x)
x

r
y

 xy 
 26
 0 . 65
x
 x2 20

Y  8   0 . 65 ( X  6 )  Y  11 . 9  0 . 65 X
Dr.K.KAVITHA
4. In a partially destroyed record, the following data and legible:
Variance of X=25. Regression equation of X on Y is 5X-Y=22 and
regression equation of Y on X is 64X-45Y=24.
Find 1)Mean values of X and Y 2)Coefficient of correlation between
X and Y and (3) Standard deviation of Y.

Ans:1) X  x  6; Y  y  8

Rewrite equation 1 and 2

    y 
  r x  r   r2
2) r  8 /15 (   y   x 
  

40  1
  13.33(or) 
3) y
( r x    y  5.r. x
3 y 5

(given V(X)=25  x  V ( X )  25  5 )

Dr.K.KAVITHA