Probability and Statistics

Course Code: - BS-301

Lecture-03

Dr. Bulbul Jan 1

Frequency Distribution

Chapter 02

2
 Frequency distribution
• The arrangement of a set of data in a table showing the
distribution of the data into classes or groups together with the
number of observations in each class or group is called a Frequency
Distribution.
• The number of observations falling in a particular class is referred
to as the class frequency of simply frequency, and is denoted by f.
• Summarized data by distributing into classes or categories with
their frequencies.

3
 What is Grouped and Ungrouped data?

• When data is small, and presented in original form, it is

called ungrouped data.
• When data is large, it is distributed into frequencies,
called grouped data.

4
4
• Class limits/Intervals: - The class limits are defined as the
numbers or the values of the variables which describe the
classes, the smaller number is called lower class limit and
the larger number is called upper class limit.
• Class limits should be non-overlapping i.e. 10-14, 15-19,
20-24, 25-29 etc.
• The values equal to upper/lower limit and falling between
them should be included to make frequency table.

5
Class boundaries: -
• The numbers which separate one class from another are called
class boundaries.
• A class boundary is located midway between the upper limit of a
class and the lower limit of the next higher class.
• For the above example it is 9.5 – 14.5, 14.5 – 19.5, 19.5 – 24.5,
24.5 – 29.5 etc.
• The upper class boundary and the lower class boundary of next
class are same.
• Class boundary takes always one more decimal place than the
class limit, so that the possibility of any observation falling exactly
on the boundary is avoided.

6
Midpoint / Class mark: -
• A midpoint is number which divides each class into two
equal parts.
• It is obtained by dividing either the sum of the lower and
upper limits or boundaries of a class by 2.
• For the above example, these are 12, 17, 22, 27 etc.

7
• Class Width: - The class width is equal to the
difference between the class boundaries.
Or
• Difference between two successive midpoints
Or
• Difference between two successive lower class limits.
• Class width of the above example is 5.

8
 Constructing a grouped frequency distribution:
Step-01 Determine the number of classes:
Now how to make classes, if number of classes is not
mentioned?
• First decide the number of classes.
• There are no any specific rules for deciding the exact number
of classes. But as a general rule the number of classes should
be between 5 and 20.
• Actually the number of classes depends on the size of data.
• then find class width.

9
Step-02 Determine the Class width (h):

L arg est value  lowest value

Class width 
number classes

•The width is denoted by h.

•In case of friction the next higher whole number is
usually taken as the width class interval.
•These rules are applied to group raw data.

10
Step-03 Deciding Starting Point (Lower limit of the first class):

•The starting point should be minimum value or less than the

minimum value of the data.

Step-04 Deciding the nature of the class (Discrete or continuous):

•Practically it is impossible to have continuous data because the
values are round off up to a certain decimal places and therefore we
always construct discrete classes.
Step-05 Determining the remaining classes.
Step-06 Distribute the data and total the frequency column.
11
Example: 01 The following is the record of marks
obtained by 60 students in an examination. Construct
a frequency distribution table by taking 5 as class
interval.

76 79 81 86 86 89 89 90 91 94
95 96 96 97 99 100 100 101 101 101
102 104 104 104 105 106 106 107 108 108
109 109 109 110 110 111 112 113 114 115
116 116 117 117 118 119 120 121 122 123
124 125 128 129 129 131 134 134 135 135

12
 Solution:
• From this table 76, 81, 86, 91,… are called lower Grouped Frequency Distribution
limits of class intervals while 80, 85, 90,……. are Class interval Frequency
called upper limit of the class intervals. 76 – 80 2
81 – 85 1
• The length of each class is said to be the size or 86 – 90 5
width of the class interval denoted by h. here h=5 91 – 95 3
96 – 100 6
• The above frequency distribution is said to be 101 – 105 8
discrete type of frequency distribution. 106 – 110 10
111 – 115 5
• But some times we are required continuous type of 116 – 120 7
frequency distribution, for this purpose we convert 121 – 125 5
class limits into class boundaries by adding and 126 – 130 3
subtracting a certain amount in the class limits. 131 – 135 5
Total 60
13
Example:02 The weights of 50 football players are given
below. Construct a frequency distribution table with 10
classes beginning with 190.

193 240 217 283 268 212 251 263 275 208
230 288 259 225 252 236 243 247 280 234
250 236 277 218 245 268 231 269 224 259
258 231 255 228 202 245 246 271 249 255
265 235 243 219 255 245 238 257 254 284

14
Solution:
Range = largest number – smallest number
Class interval Tally Marks Frequency
= 290 – 190 = 100,
190 – 199 / 1
Class width (h) = 100/10 200 – 209 // 2
h = 10 210 – 219 //// 4
220 – 229 /// 3
230 – 239 /// 8
240 – 249 //// 9
250 – 259 / 11
260 – 269 5
270 – 279 /// 3
280 – 289 //// 4
Total 50
15
Example:03 The following data showing the marks of 25
students;
26 35 42 43 51
28 36 42 43 51
29 39 42 46 52
31 40 43 46 52
32 40 43 46 55
Arrange in a simple frequency distribution and grouped
frequency distribution.

16
Solution: Marks No. of Marks No. of students/
students/ Frequency
Frequency
26 1 40 2
28 1 42 3
29 1 43 4
31 1 46 3
32 1 51 2
36 1 52 2
39 1 55 1

• The above arrangement of data is suitable for a small number of data

points, if there are huge number of data points then the above method is
not be helpful for applications, but to get still better idea of the structure
of the frequency distribution, we reclassify the data into classes (or class
intervals) as follow
17
 Grouped Frequency Distribution
Class interval Tally Marks Frequency
26 – 30 /// 3
31 – 35 /// 3
36 – 40 //// 4
41 – 45 7
46 – 50 /// 3
51 – 55 5

Total  f  25

SHAFQAT ALI LASHARI 18

Relative Frequency Distribution:
A relative frequency distribution consists of the relative frequencies, or
proportions (percentages), of observations belonging to each class.
If f1 , f 2 , .........., f k are frequencies of k-class in a frequency distribution
and  f is the sum of all frequencies then
f1 f2 fk
, , ........,
 f  f  f
are called the relative frequencies. The sum of all relative frequencies
must be unity. This is called relative frequency distribution.
They give the chance or probability of getting an observation from each
class.

19
Example-01: Find relative frequency distribution to the
following frequency distribution.

Class Interval 2-4 5-7 8-10 11-13 14-16 Total

Frequency (f) 1 3 4 5 2 15

20
Solution:
Since, total of all frequencies :  f  15
Class Interval Frequencies (f) Relative Frequency
2-4 1 1/15=0.07
5-7 3 3/15=0.20
8-10 4 4/15=0.27
11-13 5 5/15=0.33
14-16 2 2/15=0.13
Total 15 1.00
In above table each class has its relative frequency and the sum of all relative
frequencies is unity.
Therefore, we have a relative frequency distribution.
21
Cumulative Frequency:
•The total frequency of a variable from its one end to a certain value
(usually upper class boundary in grouped data), is known as cumulative
frequency. Cumulative frequency of the last class is the sum of all
frequencies in the distribution.
•In a frequency distribution the number of values or frequencies occur
between the upper and lower limits (or boundaries).
•But If the number of values occur under the upper boundary of a class that
frequency is known as “less than cumulative frequency distribution” .
•Similarly, if the number of values occur above or over the lower boundary
of a class that frequency is known as “more than cumulative frequency”.
•The distributions for less than or more than values obtained in this way are
called cumulative frequency distributions for less than and more than types.
22
Example-01:
Find cumulative frequency distributions for less than and more than
values of the following frequency distribution.

Class Interval 2-5 6-9 10-13 14-17 18-21 Total

Frequency (f) 1 3 8 6 2 20

SHAFQAT ALI LASHARI 23

Solution:
First, we find class boundaries , i.e.
Class Intervals Class Boundaries Frequencies (f)
2-5 1.5-5.5 1
6-9 5.5-9.5 3
10-13 9.5 13.5 8
14-17 13.5-17.5 6
18-21 17.5–21.5 2
Total 20

24
 Cumulative frequency for less than Cumulative frequency for more than
Less than or U.C.B C.f. More than or L.C.B C.f.

Less than 5.5 1 1.5 or more 20

Less than 9.5 4 5.5 or more 19
Less than 13.5 12 9.5 or more 16
Less than 17.5 18 13.5 or more 6
Less than 21.5 20 17.5 or more 2

Where U.C.B means upper class boundary and L.C.B means lower class boundary

25
Example-02:
Following raw data showing ages in years of 20 children's studying in a school.
4.9 3.2 4.3 3.5 6.1 5.3 2.6 3.8 3.3 4.6
4.1 4.6 3.6 5.1 3.9 5.8 4.3 4.6 3.2 3.3
a) Construct a frequency table by taking a class interval of one year.
b) Find Class boundaries and mid-values.
c) Find relative frequency distribution.
d) Prepare “less than” and “more than” types of cumulative frequency tables.

26
Solution:
Since Mini mum age=2.6 and Maximum age=6.1 therefore, frequency
distribution(table) for ages of 20 children is given below
a) Construct a frequency table by taking a class interval of one year.
Ages in years Tally Marks Number of children
C.I. f
2.5-3.4 //// 4
3.5-4.4 8
4.5-5.4 / 6
5.5-6.4 // 2
Total 20

27
b) Find Class boundaries and mid-values.

Ages in years Frequency C.B. Mid Values

C.I. (f)
2.5-3.4 4 2.45-3.45 2.95
3.5-4.4 8 3.45-4.45 3.95
4.5-5.4 6 4.45-5.45 4.95
5.5-6.4 2 5.45-36.45 5.95
Total 20

28
c) Find relative frequency distribution.

Ages in years Frequency Relative Frequency

C.I. (f)
2.5-3.4 4 4/20 = 0.2
3.5-4.4 8 8/20 = 0.4
4.5-5.4 6 6/20 = 0.3
5.5-6.4 2 2/20 = 0.1
Total 20 1.0

29
d) Prepare “less than” and “more than” types of cumulative frequency tables.

For less than For more than

Ages in years C.f. Ages in years C.f.
Less than 3.45 4 2.45 or more 20
Less than 4.45 12 3.45 or more 16
Less than 5.45 18 4.45 or more 8
Less than 6.45 20 5.45 or more 2

30
Question 3: The table below gives the values of temperature recorded in
Hyderabad for 25 days in summer. Represent the data in the form of less than
type cumulative frequency distribution:

Dr. Bulbul Jan 31

Solution:
Since there are so many distinct values here, we will use grouped frequency distribution.
Let’s say the intervals are 20-25, 25-30, 30-35.
Frequency distribution table can be made by counting the number of values lying in these
intervals.

Temperature Number of days Cumulative frequency

20-25 2 2
25-30 10 12
30-35 13 25

Dr. Bulbul Jan 32