Rank Correlation

RANK CORELATION
GROUP MEMBERS
ISMA SHAZAD 18102015-015
KHUBAN KHAN 18102015-010
ASLAN 18102015-006
SAAD SHEIKH 18102015-001
MUHAMMAD JABER BUTT 18102016-001 (MBA 2.5)
Outline
1. What is Ranking? 9. Pearson’s Rank

2. What is Correlation? Correlation
3. Types of Correlation 10. Pearson’s Rank
Correlation Example
4. What is Rank Correlation?
11. Spearman’s Rank
5. Why Rank Correlation? Correlation
6. Advantages 12. Assumptions of
7. Disadvantages Spearman’s Rank
8. Major Methods to find Correlation
Rank Correlation 13. Spearman’s Rank
Correlation Steps
What is Ranking?
A ranking is a relationship between a set of items

such that, for any two items, the first is either 'ranked
higher than', 'ranked lower than' or 'ranked equal to'
the second.
What is Correlation?
“In the broadest sense correlation is any statistical

association.”
 Though in common usage it most often refers to how

close two variables are to having a linear relationship with
each other.
What is Correlation CONT.
 If the quantities (x ,y) vary in such a way that change in

one variable corresponds to change in other variable
then the variables x and y are correlated.
Types of Correlation
 Positiveand negative
 Simple partial and multiple
 Linear and non linear
What is Rank Correlation?
 In statistics a rank correlation is any of several statistics

that measure an ordinal association.
“where ordinal association mean the relationship between

rankings of different ordinal variables or different rankings of
the same variable.”
What is Rank Correlation CONT.
 Similarly, A rank correlation coefficient measures the

degree of similarity between two rankings, and can be
used to assess the significance of the relation between
them.
Why Rank Correlation?
It is possible to avoid making any assumptions about the

populations being studied by ranking the observations
according to size and basing the calculations on the ranks
rather than upon the original observations. It does not
matter which way the items are ranked, item number one
may be the largest or it may be the smallest. Using ranks
rather than actual observations gives the coefficient of rank
correlations.
Advantages
 When the intervals between data points are problematic

,it is advisable to study the rankings rather than the actual
data.
 Can be used to reduce the weight of outliers(large
distance get treated as one rank difference).
Disadvantages
 Calculations for finding the relation may become tedious.

 Additionally ties are important and must be forces into
computation.
Major Methods to find Rank
Correlation
Usually there are four methods of calculating rank
correlation used in statistics but only two are
commonly known to be used quite often.
 Pearson’s Rank Correlation
 Spearman's Rank Correlation
Pearson’s Rank Correlation
The standard formula used in computation of

Pearson’s Rank Correlation Coefficient is as follows
Pearson’s Rank Correlation CONT.
Pearson’s Rank Correlation CONT.
Pearson’s Rank Correlation
Example
Calculate the Correlation of the Following Data
Subject Scores in Test 1 Scores in Test 2

A 5 12
B 3 15
C 2 11
D 8 10
E 6 18
Pearson’s Rank Correlation Example
CONT.
Subject Scores in Scores in XY X2 Y2
Test 1 (X) Test 2 (Y)
A 5 12 60 25 144
B 3 15 45 9 225
C 2 11 22 4 121
D 8 10 80 64 100
E 6 18 108 36 324
N=5 ΣX = 24 ΣY = 66 ΣXY = 315 ΣX2 = 138 ΣY2 = 914
Pearson’s Rank Correlation Example
CONT.
Spearman’s Rank Correlation
Where n is the number of data points of the two variables

and D is the difference in the ranks of the ith element of
each random variable considered. The Spearman
correlation coefficient, rs, can take values from +1 to -1
Assumptions of Spearman’s Rank
Correlation
 The data consists of bivariate random variables.
 The measurement method is at least ordinal.
 X and Y are independent.
Spearman’s Rank Correlation Steps
 Step 1
Draw the table like:
CONT.
 Step 2
Fill the data field with the given data
CONT.
 Step 3
Give the Rank for the data
CONT.
 Step 4
Find the difference d & d2
CONT.
 Step 5
Apply the formula:
Where
d = difference
n = no. of data
Putting the value:-
ρ=1-6(6)
3(9-1)
ρ=1-36
3(8)
ρ=35
24
ρ=1.45
Spearman’s Rank Correlation
Example
 A composite rating is given by executives to
each college graduate joining a plastic
manufacturing firm. The executive ratings
represent the future potential of the college
graduate. The graduates then enter an in-plant
training program and are given another
composite rating. The executive ratings and the
in-plant ratings are as follows:
Spearman’s Rank Correlation Example
CONT. Graduate Executive Rating (X) Training Rating (Y)
A 8 4
B 10 4
At the 5% level of C 9 4
significance, D 4 3
determine if there is a E 12 6
positive correlation F 11 9
G 11 9
between the variables
H 7 6
Find the rank I 8 6
correlation coefficient J 13 9
if the null is rejected K 10 5

L 12 9

Rank Correlation

Uploaded by

Copyright:

Available Formats

Rank Correlation

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Rank Correlation

Uploaded by

Copyright:

Available Formats

RANK CORELATION

1. What is Ranking? 9. Pearson’s Rank

A ranking is a relationship between a set of items

“In the broadest sense correlation is any statistical

 Though in common usage it most often refers to how

 If the quantities (x ,y) vary in such a way that change in

 In statistics a rank correlation is any of several statistics

“where ordinal association mean the relationship between

 Similarly, A rank correlation coefficient measures the

It is possible to avoid making any assumptions about the

 When the intervals between data points are problematic

 Calculations for finding the relation may become tedious.

The standard formula used in computation of

Subject Scores in Test 1 Scores in Test 2

Where n is the number of data points of the two variables

if the null is rejected K 10 5

You might also like