Measures of Non-Central Position

 Often referred to as fractiles or quantiles

 Describe or locate the position of certain noncentral pieces of data relative to the entire set of
data
 Values below which a specific fraction or percentage of the observations in a given set must fall
 Most common fractiles: quartiles, deciles and percentiles

 These are important measures which divide the distribution into parts of subgroups.
 Percentiles are used to divide the distribution into one hundred parts.
 Deciles divide the distribution in to 10 subgroups.
 Quartiles divide the distribution into four subgroups.
 These measures are also important in looking at the position of an individual in a group.
 This may be also used in categorizing data.

When presenting or analysing data set it is sometimes important to group subjects into several equal
groups.

For example, to create four equal groups we need the values that split the data such that 25% of the
observations are in each group.

The cut off points are called quartiles and there are three (3) of them (the middle one also being called
the median).

20, 22, 25, 27, 28, 29, 30, 31, 33, 35, 39, 40

20, 22, 25, 27, 28, 29, 30, 31, 33, 35, 39, 40

20, 22, 25, 27, 28, 29, 30, 31, 33, 35, 39, 40

Other values likely to be encountered are deciles, which split data into 10 parts and percentiles which
split the data into 100 parts (also called centiles).
Quartiles

 Values that divide a set of observations into 4 equal parts

 Denoted by Q1, Q2 and Q3
 25% of the data falls below Q1
 50% falls below Q2
 75% falls below Q3

20, 22, 25, 27, 28, 29, 30, 31, 33, 35, 39, 40

 1st quartile, Q1, or 25th percentile—the number that separates the lowest 25% of the group
from the highest 75% of the group.
 2nd quartile, Median, or 50th percentile—the number in the middle of the group, when
arranged from smallest to largest.
 3rd quartile, Q3, or 75th percentile—the number that separates the lowest 75% of the group
from the highest 25% of the group.
 Maximum, or (rarely) “100th percentile”—the largest number in the group.

Quartiles are used to summarize a group of numbers. Instead of looking a big list of numbers,
you are looking at just a few numbers that give you a picture of what’s going on in the big list.
Quartiles are great for reporting on a set of data and for making box and whisker plots. Quartiles
are especially useful when you’re working with data that isn’t symmetrically distributed, or a data
set that has outliers.

All numerical summaries—like mean, median, and mode—give you a few numbers to summarize
a large group of data, but what’s special about quartiles is that they split the data up into four
equal-size groups.

The quartiles for ungrouped data

The following are the formula for Q1, Q2, Q3:

Q1 = n/4

Q2 = 2n/4

Q3 = 3n/4
Example: Find the first, second and third quartiles of the ages of 10 middle management employees of a
certain company. The ages are 53, 45, 59, 48, 54, 46, 51, 57, 58, and 55.

Step 1: Arrange data in order:

45, 46, 48, 51, 53, 54, 55, 57, 58, 59

Step 2:

Q1 = n/4

Q2 = 2n/4

Q3 = 3n/4

Q1 = 10/4

=2.5th observation

Since the 2.5th falls between 46 and 48, we need to get the average of the two values.

Q1 = 46+48

=94/2

Q1=47

Q2 = 2(10)/4

=20/5

=5th observation

Q2 = 53

Q3 = 3(10)/4

=30/4

=7.5th observation

Since the 7.5th falls between 55 and 57, we need to get the average of the two values.

Q3 = 55+57

2
Q3 = 56

In descriptive statistics, a box plot or boxplot is a method for graphically depicting groups of
numerical data through their quartiles. Box plots may also have lines extending from the boxes
indicating variability outside the upper and lower quartiles, hence the terms box-and-whisker plot and
box-and-whisker diagram.

Example:

The following is a list of scores resulting from an English examination administered to 40 students:

Scores (x)

91 61 46 62 54

62 93 90 99 76

48 83 59 96 66

94 52 51 59 62

89 100 92 70 59

91 73 68 49 54

85 43 78 50 45

98 69 77 42 46
Solution:

Arrange the scores from the lowest to the highest:

Scores (x)

42
43
45
46
46
48
49
50
51
52
54
54
59
59
59
61
62
62
62
66
68
69
70
73
76
77
78
83
85
89
90
91
91
92
93
94
96
98
99
100

For Q1 = n/4

=40/4

=10

Q1 = 10th observation (52)

For Q2 = 2n/4

=2(40)/4

=80/4

=20

Q2 = 20th observation (66)

For Q3 = 3n/4

=3(40)/4

=120/4

=30

Q3 = 30th observation (89)

The following data are the heights of 40 students in a statistics class.

59 60 61 62 62 63 63 64 64 64 65 65 65 65 65 65 65 65 65 66 66
67 67 68 68 69 70 70 70 70 70 71 71 72 72 73 74 74 75 77
Construct a box plot with the following properties; the calculator
instructions for the minimum and maximum values as well as the quartiles
follow the example.

Minimum value =

Maximum value =

Range =

Q1, First quartile =

Q2, Second quartile or median=

Q3, Third quartile =

Deciles

Values that adivide a set of observation into 10 equal parts

Denoted by D1, D2,…9

10% of the data falls below D1

20% falls below D2

90% falls below D9

Solved in exactly the same way for the quartiles, except for the denominator

k= (i/10)n

The Deciles for Ungrouped Data

The formula for decile is:

Dk = Kn/10

Where:

D = decile

K = from 1, 2, … 9

n = sample size

The following is a list of scores resulting from an English examination administered to 40 students
(arranged in an array form from lowest to highest). Solve for D3, D5 and D8.

42 54 68 90

43 54 69 91

45 59 70 91

46 59 73 93

46 59 76 93

48 61 77 94

49 62 78 96

50 62 83 98

51 62 85 99

52 66 89 100

Solution:

D3 = 3n/10

=3(40)/10

=120/10
=12

D3 = 12th observation (54)

D5 = 5n/10

=5(40)/10

=200/10

=20

D5 = 20th observation (66)

D8 = 8n/10

=8(40)/10

=320/10

=32

D8 = 32nd observation (91)

Percentiles

 Values that divide a set of observations into 100 equal parts

 Denoted by P1, P2, …P99
 1% of the data falls below P1
 2% of the data falls below P2
 99% of the data falls below P99
Percentiles for ungrouped data

The formula for percentile is:

Pk = kn/100

Where:

P = percentile

k = from 1, 2, 3,…99

n = sample size

Below are the scores of 40 students in an English examination. Solve for P50, P66, P98.

42 54 68 90

43 54 69 91

45 59 70 91

46 59 73 93

46 59 76 93

48 61 77 94

49 62 78 96

50 62 83 98

51 62 85 99

52 66 89 100

It can be noted that the position of the score of 66 in the above distribution are the same when the
following measures are computed such as the Md = Q2 = D5 = P5

So the Md = Q2 = D5 = P50

Md = 20th = 66

Q2 = 20th = 66

D5 = 20th = 66
P50 = 20th = 66

Quartiles for Grouped Data

𝑘𝑁
4
−𝑐𝑓
Qk = LB + ( )i
𝑓

Where Qk = quartile

N = population

k = quartile location

LB = lower boundary of the quartile class

f = frequency of the quartile class

cf = cumulative frequency before the quartile class

i= class interval

Example: Determine the Q1, Q2 and Q3 of the frequency distribution on the ages of 50 people taking
travel tours.

Class Frequency

18-26 3

27-35 5

36-44 9

45-53 14

54-62 11

63-71 6

72-80 2
Solution:

Step 1: Construct a cumulative frequency column.

Class F cf

18-26 3 3

27-35 5 8

36-44 9 17

45-53 14 31

54-62 11 42

63-71 6 48

72-80 2 50

Step 2: Determine the Q1 Class.

Q1 (Rank value) = N/4

=50/4

=12.5

Step 3: Identify the Q1 class by locating the 12.5th rank

Class

Class F cf

18-26 3 3

27-35 5 8

36-44 9 17 Q1 class

45-53 14 31

54-62 11 42

63-71 6 48

72-80 2 50
Step 4: Determine the values of LB, cf, f, i and N.

LB = 36-0.5

=35.5

cf = 8

f=9

i = 45-36 = 9

𝑘𝑁
4
−𝑐𝑓
Qk = LB + ( )i
𝑓

Q1= 44.5 + (50/4) - 8 (9)

9
Q1 = 40
Thus, the Q1 is 40, observed that the Q1 will fall within the class
boundary of Q1 class.

Step 6: Apply the same procedure to obtain the values of Q2

and Q3.
Locate the second quartile rank:
2N = 2(50) = 25
4 4

Class F cf

18-26 3 3

27-35 5 8

36-44 9 17

45-53 14 31 Q2 Class

54-62 11 42

63-71 6 48

72-80 2 50
LB = 45-0.5 = 44.5
𝑘𝑁
4
−𝑐𝑓
Qk = LB + ( )i
𝑓
 2(50) 
 
Q2= 44.5   4  17 9
 14 
 
 

Q2 = 49.64

Class F cf

18-26 3 3

27-35 5 8

36-44 9 17

45-53 14 31

54-62 11 42 Q3 Class

63-71 6 48

72-80 2 50

LB = 54-0.5
LB = 53.5

𝑘𝑁
4
−𝑐𝑓
Qk = LB + ( )i
𝑓
 3N 
  cf 
Q3  LB   4 i
 f 
 
 

 3(50) 
  31 
Q3  LB   4 9
 11 
 
 
Q3 = 58.82

Deciles for Grouped Data

 k(N ) 
  cf 
Dk  LB  10 (i)
 f 
 
 
Where:

Dk = decile

N= population

k = decile location

LB = lower boundary of the decile class

f = frequency of the decile class

Cf = cumulative frequency before the decile class

i = class interval

Example:

Determine the D7 of the frequency distribution on the ages of 50 people taking travel tours.

Class f

18-26 3

27-35 5

36-44 9

45-53 14

54-62 11

63-71 6

72-80 2

Solution:

Step 1: Construct a cumulative frequency column in a table.

Class f cf

18-26 3 4
27-35 5 8

36-44 9 17

45-53 14 31

54-62 11 42

63-71 6 48

72-80 2 50

Step 2: Determine the D7 class

7( N ) 7(50)
D7 (Rank value) =   35
10 10
Step 3: Identify the D7 class by locating the 35th rank in the table.

Class f cf

18-26 3 4

27-35 5 8

36-44 9 17

45-53 14 31

54-62 11 42 D7 class

63-71 6 48

72-80 2 50

Step 4: Determine the values of LB, cf, i, and N.

LB = 54-0.5

LB = 53.5

cf = 31

f = 11

i = 54-45 = 9

Step 5: Apply the formula to compute for the value of the seventh decile.

 k(N ) 
  cf 
Dk  LB  10 (i)
 f 
 
 
  7(50) 
  31 
D7  53.5  10 (9)
 11 
 
 
D7 = 56.77

Percentiles for grouped data

 k(N ) 
  cf 
Pk  LB  100 (i )
 f 
 
 
Where:

Pk = percentile

N= population

k = decile location

LB = lower boundary of the decile class

f = frequency of the decile class

Cf = dumulative frequency before the decile class

i = class interval

Step 1: Determine the P22 Class.

22 N 22(50)
P22 rank value =   11
100 100

Step 2: Identify the P22 class by locating the 11th rank in the table.

Class f cf

18-26 3 4

27-35 5 8
36-44 9 17 P22 Class

45-53 14 31

54-62 11 42

63-71 6 48

72-80 2 50

Step 3: Determine the values of LB, cf, f, i and N.

LB = 36-0.5 = 35.5

i = 45-36 = 9

Cf = 8

f=9

 k(N ) 
  cf 
Pk  LB  100 (i )
 f 
 
 

 22(50) 
 8
P 22  35.5  100 (9)
 9 
 
 
P22 = 38.5