Statistics and Probability

Quarter 4 Lesson 3.1

Constructing a Frequency Distribution Table

Prepared by: K.A.R. Aspiras-Lorenzo

 Consider the following data
40 43 44 45 45 45 45 49 50 51
51 51 51 52 53 53 54 54 56 56
56 56 57 58 58 58 58 58 59 59
59 60 60 60 61 61 61 61 62 62
62 63 63 63 63 63 63 64 64 64
64 64 64 65 65 65 65 65 65 65
66 67 67 67 68 68 68 68 69 69
69 69 69 70 70 70 70 70 70 70
70 71 71 71 71 71 71 71 71 72
72 72 73 73 73 73 73 73 73 73
73 74 74 74 75 75 75 76 76 76
76 76 76 76 77 77 77 77 77 77
77 78 78 78 78 78 78 78 78 79
79 79 79 79 80 80 80 80 80 80
80 80 80 80 80 81 81 81 81 81
81 81 82 82 82 82 82 82 83 83
83 84 84 84 85 85 85 85 85 85
Prepared by K.A.R. Aspiras-Lorenzo
 Step 1
Determine the adequate number of classes, K .
• This will depend on the number of observations and size of the
class interval.
• Generally, larger data sets will require more classes.
• There are no strict rules regarding the number of classes in a
frequency distribution.

Prepared by K.A.R. Aspiras-Lorenzo

 Step 1
Determine the adequate number of classes, K .
• Note that the more classes we include, the more details we
retain
• If there are too many classes, then the frequency distribution
will already lose its value for effectively summarizing the data

Prepared by K.A.R. Aspiras-Lorenzo

 Step 1
Determine the adequate number of classes, K .
• For approximation to the number of classes, we can use Sturge’s
rule.
𝐾 = 1.322 log 𝑛
Where K = suggested number of classes;
log = ordinary logarithm (base 10); and
n = number of observations

Prepared by K.A.R. Aspiras-Lorenzo

 Considering the given data
Formula: 𝐾 = 1.322 log 𝑛
n = 170

Solution:
𝐾 = 1.322 log 170
K = 2.95

We can initially consider 3 classes

Prepared by K.A.R. Aspiras-Lorenzo
 Step 2
Determine the range, R

𝑅 = ℎ𝑖𝑔ℎ𝑒𝑠𝑡 𝑜𝑏𝑠𝑒𝑟𝑣𝑒𝑑 𝑣𝑎𝑙𝑢𝑒 − 𝑙𝑜𝑤𝑒𝑠𝑡 𝑜𝑏𝑠𝑒𝑟𝑣𝑒𝑑 𝑣𝑎𝑙𝑢𝑒

Considering the given data:

Highest value = 85
Lowest value = 40

𝑅 = 85 − 40
R = 45

Prepared by K.A.R. Aspiras-Lorenzo

 Step 3
′ 𝑹
Compute for 𝑪 =
𝑲

Consider the values that we have just computed

R = 45
K=3
′ 45
𝐶 =
3
C’ = 15
Prepared by K.A.R. Aspiras-Lorenzo
 Step 4

Determine the class size, C, by rounding-off C’ to a convenient

number.

• Whenever possible, all classes should be of the same size

Prepared by K.A.R. Aspiras-Lorenzo

 Step 4

Determine the class size, C, by rounding-off C’ to a convenient

number.

• If classes are not equally wide, it becomes difficult to tell

whether differences in class frequencies result mainly from
differences in concentration of items or from differences in the
class widths

Prepared by K.A.R. Aspiras-Lorenzo

 Step 4

Determine the class size, C, by rounding-off C’ to a convenient

number.

• Note that there are certain instances when it is not practical to

use equal sizes such as when the distribution is badly skewed.

Prepared by K.A.R. Aspiras-Lorenzo

 Step 5
Choose the lower class limit of the first class.
Make sure that the smallest observation will belong in the first
class.

Considering the given data, we can choose 40 as the lower class

limit of the first class

Prepared by K.A.R. Aspiras-Lorenzo

 Step 6
List the class intervals.
• Determine the lower class limits of the succeeding classes by
adding the class size to the lower class limit of the previous class.
• Obtain the upper class limit by obtaining the same number of
significant digits.
• The last class should include the largest observation

Prepared by K.A.R. Aspiras-Lorenzo

 Step 6
Considering our given data:
𝐿𝐶𝐿 𝑜𝑓 𝑛𝑒𝑥𝑡 𝑐𝑙𝑎𝑠𝑠 𝑖𝑛𝑡𝑒𝑟𝑣𝑎𝑙
= 𝐿𝐶𝐿 𝑜𝑓 𝑝𝑟𝑒𝑐𝑒𝑑𝑖𝑛𝑔 𝑐𝑙𝑎𝑠𝑠 𝑖𝑛𝑡𝑒𝑟𝑣𝑎𝑙 + 𝐶
Lower Class Limit Upper Class Limit
40 54
40 + 15 = 55 55 69
55 + 15 = 70 70 84 84 + 15 = 99
70 + 15 = 85 85 99
Prepared by K.A.R. Aspiras-Lorenzo
 Step 6
We now have the following class intervals

40 – 54
55 – 69
70 – 84
85 – 99

Prepared by K.A.R. Aspiras-Lorenzo

 Step 7
Tally the observed values in each class interval
Class
Tally
Interval
40 – 54
55 – 69

70 – 84

85 – 99
Prepared by K.A.R. Aspiras-Lorenzo
 Step 8
Sum the frequency column and check against the total number of observations

Class
Tally f
Interval
40 – 54
18
55 – 69
55
70 – 84 91
85 – 99 6
TOTAL
170
Prepared by K.A.R. Aspiras-Lorenzo
 The simplest frequency distribution table
that we can produce is the following:

Class Interval f
40 – 54 18
55 – 69 55
70 – 84 91
85 – 99 6
TOTAL 170
Prepared by K.A.R. Aspiras-Lorenzo
 But we can further extend it by getting the
class boundaries and the class mark.

Class
Class Boundaries Class
f
Interval Mark
LCB UCB
40 – 54 18 39.5 54.5 47
55 – 69 55 54.5 69.5 62
70 – 84 91 69.5 84.5 77
85 – 99 6 84.5 99.5 92
TOTAL 170
Prepared by K.A.R. Aspiras-Lorenzo
 Relative Frequency

The class frequency divided by the total number of observations

𝑐𝑙𝑎𝑠𝑠 𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦
𝑅𝐹 =
𝑡𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑜𝑏𝑠𝑒𝑟𝑣𝑎𝑡𝑖𝑜𝑛𝑠

Prepared by K.A.R. Aspiras-Lorenzo

 Relative Frequency Percentage
The relative frequency multiplied by 100

𝑅𝐹𝑃 = 𝑅𝐹 × 100

Prepared by K.A.R. Aspiras-Lorenzo

 Going back to our table:

Class
Class Boundaries Class
f RF RF X 100
Interval Mark
LCB UCB
40 – 54 18
18 39.5 54.5 47 = 0.11 11
170
55 – 69 55
55 54.5 69.5 62 = 0.32 32
170
91
70 – 84 91 69.5 84.5 77 = 0.54 54
170
85 – 99 6
6 84.5 99.5 92 = 0.04 4
170
TOTAL 170 1.01 ≈ 1 101 ≈ 100
Prepared by K.A.R. Aspiras-Lorenzo
 Cumulative Frequency Distribution
• It is another variation of the frequency distribution
• This is used to determine how many observations have values
smaller than or greater than a specified class boundary
• It shows the accumulated frequencies of successive classes, either
at the beginning or at the end of the distribution

Prepared by K.A.R. Aspiras-Lorenzo

 2 Types of Cumulative Frequency
Distribution
• Less than cumulative frequency distribution (<CFD)
• Greater than cumulative frequency distribution (>CFD)

Prepared by K.A.R. Aspiras-Lorenzo

 Less than cumulative frequency
distribution (<CFD)
• The less than cumulative frequency of the first class interval is its
class frequency
• To get the less than cumulative frequency of the second class, we
add the less than cumulative frequency of the first class to the
class frequency of the second class.

Prepared by K.A.R. Aspiras-Lorenzo

 Less than cumulative frequency
distribution (<CFD)
• Repeat the procedure for the rest of the classes
• The less than cumulative frequency of the last class interval must
be the same as the total number of observations

Prepared by K.A.R. Aspiras-Lorenzo

 Class
Class Boundaries Class RF X
f RF <CFD
Interval Mark 100
LCB UCB
40 – 54 18 39.5 54.5 47 0.11 11 18
55 – 69 55 54.5 69.5 62 0.32 32 73
70 – 84 91 69.5 84.5 77 0.54 54 164
85 – 99 6 84.5 99.5 92 0.04 4 170
TOTAL 170 1.01 ≈ 1 101 ≈ 1

Prepared by K.A.R. Aspiras-Lorenzo

 Greater than cumulative frequency
distribution (>CFD)

• The greater than cumulative frequency of the first class interval

is the total number of observations.
• Subtract the frequency of the first class from the greater than
cumulative frequency of the first class to get the greater than
cumulative frequency of the second class.

Prepared by K.A.R. Aspiras-Lorenzo

 Greater than cumulative frequency
distribution (>CFD)

• Repeat the process for the succeeding classes.

• The greater than cumulative frequency of the last class must be
the same as the class frequency of the last class.

Prepared by K.A.R. Aspiras-Lorenzo

 Class
Class Boundaries Class RF X
f RF <CFD >CFD
Interval Mark 100
LCB UCB
40 – 54 18 39.5 54.5 47 0.11 11 18 170
55 – 69 55 54.5 69.5 62 0.32 32 73 152
70 – 84 91 69.5 84.5 77 0.54 54 164 97
85 – 99 6 84.5 99.5 92 0.04 4 170 6

TOTAL 1.01
170 101 ≈ 1
≈1

Prepared by K.A.R. Aspiras-Lorenzo