Correlation Analysis

• Introduction
• Significance of the study of Correlation
• Types of Correlation
• Methods of Studying Correlation
 Correlation
• “Correlation” means relationship between the
values of two or more variables of the same
phenomenon or individual series. Correlation
indicates the strength of the relationship
between two variables.
• For ex: If we measure the heights and weights
of ‘n’ individuals, we assume two values – one
relating to height and the other relating to
weights.
• The statistical tool with the help of which the
relationship between two or more variables
are studied is called Correlation. The measure
of correlation is called the Correlation
Coefficient, and it tells us in one figure the
direction and degree of correlation.

• Thus correlation analysis refers to the

techniques used in measuring the closeness or
relationship between the variables.
The extent to which two or more things are related
to one another -- “co-related”

Numerical description is a correlation coefficient

Pictorial description is a scatter diagram

 Correlation Coefficient

• Number showing the degree to which two variables are

related
• Range from -1 to +1
– -1 = perfect negative correlation
– +1 = perfect positive correlation
– 0 = no relationship between the
variables
 Uses of Correlation Coefficient
1. Correlation analysis helps us in measuring the
relationship between the variables. For ex:
relation between price and demand, income
and expenditure, income and savings etc.,

2. If it is found out that the two variables are

closely related then we can estimate the value
of one variable, given the value of another with
the help of regression analysis.
3. Correlation analysis helps in analysing the
economic behaviour. For ex: Wages and the
level of inflation, savings and the rate of tax
collected etc.
4. The importance of analysing and
understanding the relationship between two
or more variables is increasing day by day
with the developments in the field of social
and economic sphere.
For ex : (i) The series of marks of individuals in
two subjects in an examination –
Accountancy and Statistics.
(ii) The series of ‘Sales revenue’ and ‘advertising
expenditure’ of different companies in a
particular year.

(iii) The series of ‘exports’ of raw cotton in

crores of rupees and ‘imports’ of finished
goods in crores of rupees for the two years.

(iv) Number of road accidents and the sale of

vehicles etc.,
 Types of Correlation
1. Positive and Negative

2. Simple, Partial and Multiple

3. Linear and non-linear.

 Positive and Negative Correlation

• Whether correlation is positive (direct)or negative

(inverse) would depend upon the direction of change
of the variable. If both variables are varying in the
same direction, i.e. if one variable is increasing , the
other variable on an average is also increasing or if
one variable is decreasing the other variable is also on
an average decreasing, the correlation is said to be
positive. OTOH, if variables are varying in opposite
direction, i.e. if one variable is increasing, the other is
decreasing or vice versa, correlation is said to be
negative.
 Positive Correlation

Over   
Number of Formal Clothing Outfits


28 


26 




 
24 

  
22  


 
20

  
  
 
18 
 




16 




14   

12 



10 

8 


6 



4  



 
2  

Over
10

15

20

25

30

35

40

45

50

55

60

65

70
5

Age of persons in household

 Negative Correlation

Over   

30 
 
28 


Number of CDs in house

  
26 

  
24 

  

22   




 


20 
 




18 



16 

  
14 
 
12 


10

8 


6 

 

4 
 

 

Over
20
10

15

20

25

30

35

40

45

50

55

60

65

70
5

Age of persons in household

 Zero Correlation

Over   
30 

  
Paper plates used monthly

28 


 


26  






 
24   





22 

 

 

  
  
20   


  


 


    
18 







 
16  





14  
   


12 



 
10 
 

8  


6  


 

4 


 

20

Over
10

15

20

25

30

35

40

45

50

55

60

65

70
5

Age of persons in household

 Positive Correlation
X Y
10 15
15 25
20 35
25 45
30 55

Positive Correlation

X Y
90 40
80 30
70 20
60 10
50 5
 Negative Correlation
X Y
10 40
20 30
30 20
40 10
50 5

Negative Correlation

X Y
100 10
90 20
80 30
70 40
60 50
• Simple, Partial and Multiple correlation.
The distinction between Simple, Partial and
Multiple correlation is based upon the
number of variables studied. When only two
variables are studied it is simple correlation.
When three or more variables are studied it is
either multiple or partial correlation.
• Linear and Non-linear (Curvilinear) Correlation
The distinction between linear and non-
linear correlation is based upon the constancy
of the ratio of change between variables. If
the amount of change in one variable tends to
bear a constant ratio to the amount of change
in the other variable, then the correlation is
said to be Linear.
If the change between the two variables is the
same, then such variables if plotted on a
graph paper, all the plotted points would fall
on a straight line.
• Non Linear or Curvilinear Correlation
Correlation would be called non-linear or curvi
linear if the amount of change in one variable
does not bear a constant ratio to the amount
of change in the other variable.
 Properties of Coefficient of
Correlation
• The value of the Karl Pearson’s Coefficient of
Correlation lies between +1 or -1. It cannote
be greater than 1 in any case.
• The Pearson’s Coefficient of Correlation is
independent of change of scale and origin of X
and Y variables.
• Pearson’s Coefficient of Correlation is the
geometric mean of regression coefficients ie.,
Correlation and Causation
Merits of Karl Pearson’s Coefficient
of Correlation
• Among the mathematical methods used for
measuring the degree of relationship , Karl
Pearson’s method is the most popular
method.
• The Pearson’s Coefficient of Correlation
summarises in one figure the degree of
correlation, but also it’s direction that is,
whether correlation is positive or negative.
Limitations of Pearson’s Coefficient
of Correlation
• The Pearson’s Coefficient of Correlation
always assumes linear relationship, regardless
of the fact whether assumption is correct or
not.
• The value of Pearson’s Coefficient of
Correlation is unduly affected by extreme
values.
• This method takes more time to compute the
value when compared to the other methods.