0% found this document useful (0 votes)
18 views22 pages

Lecture-3 Frequency Distribution

Uploaded by

fatinisraqabir
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
18 views22 pages

Lecture-3 Frequency Distribution

Uploaded by

fatinisraqabir
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 22

Lecture-3 Frequency

distribution
DS-2420 Statistics for Social Science
Jarin Musarat Chowdhury
Lecturer
Department of Development Studies
Bangladesh University of Professionals
Frequency Distribution

A frequency distribution is a set of mutually exclusive classes or categories


together with the frequency of occurrences of item, values or observations in
each class or category in a given set of data, presented usually in tabular
form.

A frequency distribution is the organization of raw data in table form, using


classes and frequencies.
It tells you how often each number appears in a set of data.
Class: Groups/categories under which each
observation will be sorted

Terms
Frequency/Class frequency: Number of
related to observation under each class
constructing
frequency Class limit: Classes that are bounded by two
values has a class limit. The smaller value is
distribution lower class limit and higher value is upper class
limit.
table Class interval: Upper class limit- Lower class
limit
Cont.
• Class mark/Class mid-point/Class value:
• Class boundary: Represents the dividing line between two adjacent class
intervals. Ensures there's no gap or overlap between groups in the
distribution.
• Open interval: When the interval is indeterminate. i.e.,
Class Class frequency

Lower class
limit
Upper class limit
Class interval= (10-5)= 5

Class midpoint=(10+5)/2= 7.5


Frequency distribution for qualitative data
Frequency distribution for quantitative
data
3, 5, 8, 7, 4, 3, 7, 2, 8, 11, 13, 9, 6, 12, 10, 4, 13, 10, 5, 11.
Array- 2, 3, 3, 4, 4, 5, 5, 6, 7, 7, 8, 8, 9, 10, 10, 11, 11, 12, 13, 13.
• Grouped distribution
• Ungrouped distribution
• Determine class width and number of classes in accordance with your
data size.
Group Frequency
Range= R= Largest value- Smallest value
2-6
Class width= h
Number of classes =k= (𝐿−𝑆)/ℎ 7-11

Total number of observation= N


12-16
“2 to the k rule”

The number classes k should be a number that makes greater than or equal to the
total observation N.
If k is determined in this way, then, h=
Or h=
Discrete and Continuous frequency
distribution
The difference of counting apples vs measuring water.
You can count each apple, can put a number on them and count the
probability of getting a specific apple. Every observation has a distinct and
countable feature. This is discrete data.
You cannot count water, put a serial number on it, measure its probability.
You can measure it, but that can give you fractions like 10.5 liters. This is
continuous data.
Discrete Data:

• Think of countable things like individual objects, categories, or whole numbers.


Imagine stairs: you can't be "halfway" between steps, each step is a distinct unit.
• Examples: Number of people in a room, Shoe size, Eye color (brown, blue,
green, etc.)
• Can be represented by counting the occurrences of each value.
• Cannot take on values between whole numbers or defined categories.
Continuous Data:
• Imagine things that can be measured along a continuum, like length, weight, or
time. Think of a ramp: you can be at any point on the ramp, not just specific steps.
• Examples: Height of a person, Temperature, Speed of a car, Duration of a phone
call
• Can be measured to any degree of precision (limited only by measuring
instruments).
• Can take on an infinite number of values within a specific range.
Wages of 50 workers
55 73 92 86 96

50 54 68 85 53

69 57 72 95 70

80 85 78 90 85

• How many workers earn less than 75?


• How many workers earn more than 55?
Wages of 50 workers
55 73 92 86 96

50 54 68 85 53

69 57 72 65 70

80 85 78 90 85

Wage Frequency
49.5- 57.5 5
57.5-65.5 1
65.5-73.5 5
73.5-81.5 2
81.5-89.5 4
89.5-97.5 3
Cumulative frequency distribution
Wage Frequency Cumulative Cumulative
frequency frequency
(percentage)

49.5- 57.5 5 5 25
57.5-65.5 1 6 30
65.5-73.5 5 11 55
73.5-81.5 2 13 65
81.5-89.5 4 17 85
89.5-97.5 3 20 100
Less than cumulative frequency
Wage Cumulative Cumulative
Frequency frequency
(percentage)

Less than 49.5 0 0

49.5- 57.5 Less than 57.5 5 25

57.5-65.5 Less than 65.5 6 30

65.5-73.5 Less than 73.5 11 55

73.5-81.5 Less than 81.5 13 65

81.5-89.5 Less than 89.5 17 85

89.5-97.5 Less than 97.5 20 100


Wage Cumulative Wage Decumulative Decumulative
Cumulativ frequency frequency frequency
e (percentage percentage
Frequency )

Less 0 49.5 or more 20 100


than 49.5
49.5- 57.5 Less 5 25 57.5 or more (20-5)= 15 75
than 57.5
57.5-65.5 Less 6 30 65.5 or more (20-6)= 14 70
than 65.5
65.5-73.5 Less 11 55 73.5 or more (20-11)= 9 45
than 73.5
73.5-81.5 Less 13 65
than 81.5 81.5 or more (20-13)= 7 35
81.5-89.5 Less 17 85
than 89.5 89.5 or more (20-17) = 3 15
89.5-97.5 Less 20 100
than 97.5 97.5 or more 0 0
Percentage distribution
i= individual group
= absolute frequency of an individual group
=Percentage frequency of an individual group
Exercise
Ages of Presidents at 57 61 57 57 58 57 61 54 68
inauguration 51 49 64 50 48 65 52 56 46
54 49 51 47 55 55 54 42 51
56 55 51 54 51 60 62 43 55
56 61 52 69 64 46 54 47 58
1. Were the data obtained from population or sample?
2. What type of measurement scale is used in the data?
3. What was the age of the youngest and the oldest president?
4. Construct a frequency distribution for the data with percentage distribution.
5. Construct a less than cumulative data frequency table for this data set.
Why is it needed?
• Unmasking Patterns and Trends: A frequency distribution takes the data points and
groups them based on their values, revealing hidden patterns and trends through which
we can see which values are common, rare, or clumped together. This helps us
understand the "shape" of data and its overall behavior.

• Making Comparisons Easy: Comparing raw data points can be messy, especially when
you have many. Frequency distributions come to the rescue by turning individual points
into clear categories and counts. Comparing these categories becomes much simpler,
allowing you to see if one group has significantly more or fewer values than another.
This empowers you to make informed comparisons and draw meaningful conclusions
• Communicating Clearly and Concisely: Sharing raw data can be overwhelming for
audiences. Frequency distributions act as translators, transforming complex data into clear
and concise summaries.

• Universal: Imagine presenting your findings to a non-technical audience. A frequency


distribution, perhaps visualized as a chart or graph, allows you to communicate key insights
effectively without drowning them in numbers.

• Foundation for Further Analysis: Frequency distributions are like the first step on a data
analysis journey. They provide a solid foundation for exploring further using more advanced
statistical techniques. Knowing how the data is distributed helps you choose the right tools
and interpret their results more accurately.

You might also like