Lecture 2 Why do we have to summarise data

• Recap
– In the previous chap you know how to collect data. Data collected

DESCRIPTIVE STATISTICS: through surveys are called ‘raw’ data.

– Raw data may include thous. obs and often provide too much

Tables and Charts information => need to summarise before presenting to audience
• Requirement
– Data summary clears away details but should give the overall
pattern.
– Summarised information are concise but should reflect the accurate
Reading materials: view of the original data
Chap 2,3 (Keller) • Methods to summarise and present data
– Tables
– Charts
– Numerical summaries (measure of location and dispersion)
1 2

Outline

• Frequency table (frequency distribution)

- Simple frequency table
- Grouped frequency table
• Charts
- Bar and pie charts
- Histograms
- Boxplot

Frequency tables
• Frequency is the number of times a certain value has
happened
• A frequency distribution records the number of
Univariate distribution times each value occurs and is presented in the form
of table
• Types of frequency distribution:
• Simple frequency distribution
• Grouped frequency distribution

5 6

1
 Simple frequency distribution Simple frequency table: example 1
• What is a simple frequency table?
– Consider each observed value as a class (group) Marks Number of students (frequency)

• Applications: 4 3

• Qualitative data 5 3

• Discrete variable with few values 6 2

• Example of discrete variable with few values 7 4

8 3
• You are given a raw data of midterm marks of 20 students as
follows: 7, 7, 10, 8, 5, 4, 5, 6, 4, 9, 8, 7, 6, 4, 8, 5, 7, 10, 10, 9 9 2

• Create a simple frequency table manually 10 3

7 8

Simple frequency distribution: Simple frequency distribution: example 2

nominal variable Nationality Number of students (frequency)
Australia 179
• Example 2: We have a data set of 686 international New Zealand 1
students studying at UNSW, Australia. Create a Hong Kong 21
frequency table Singapore 48

• Large data set => can’t create a frequency table Malaysia 70

Indonesia 76
manually
Philippines 6
• Creating a simple frequency table using SPSS Thailand 18

• Go to ‘Analyse’ => ‘Tables’ => ‘Tables of China 99

Vietnam 9
frequency’ India 11
• When the dialog box appears, choose a variable for the USA, Canada 14
box ‘Frequencies for’, then click OK UK, Ireland 35
Other Europe 42
• Copy the table to Excel for more manipulations Rest of the world 57
Total 686
9 10

Grouped FT with equal class interval:

Grouped frequency tables discrete variable with many values
Example 3: the marks scored by 58 candidates seeking promotion in
• What is a grouped frequency table? Each class a personnel selection test were recorded as follows. Construct a
include a range of observed values (class interval) frequency table using a class width of ten marks
• Applications: 37 49 58 59 56 79
62 82 53 58 34 45
• Discrete variables with many values: age
40 43 44 50 42 61
• Continuous variables 54 30 49 54 76 47

• Two types of grouped frequency tables: 64 53 64 54 60 39

49 44 47 44 25 38
• Frequency table with equal class intervals 55 57 54 55 59 40
• Frequency table with unequal class intervals 31 41 53 47 58 55
59 64 56 42 38 37
33 33 47 50
11 12

2
 Grouped FT with equal class interval:
Grouped FT with equal class interval:
discrete variable with many values (cont.)
continuous variable
Marks (class interval) Number of
candidates
(frequency)
Example 4: draw a frequency table of wages (in
21 – 30 2
USD) paid to 30 people as follows:
Note: Decision on the
31 – 40 11 number of classes and
class intervals is 202 277 554 145 361
41 – 50 17
subjective, depending on 457 87 94 240 144
51 – 60 20
the study objective. 310 391 362 437 429
61 – 70 5
176 325 221 374 216
71 – 80 2
480 120 274 398 282
81 – 90 1
153 470 303 338 209
Total 58

13 14

Grouped FT with equal class interval:

continuous variable (cont.) Grouped FT with unequal class interval

Wages (class Number of

interval) people
(frequency) Terminology: Wages per employee Number of employees

< $100 2 Lower value: the lowest value of one ≤ $60 4

$100 – < $200 5 class.
Upper value: the highest value of > $60 – ≤ $80 6
$200 – <$300 8 one class
> $80 – ≤ $90 6
Class interval: range from lower to
$300 – <$400 9
upper value > $90 – ≤ $120 6
$400 – <$500 5 Open-ended class: the first or last
classes in the range may be open- > $120 3
$500 – <$600 1 ended. That means they have no
Total 30 lower or upper values (e.g: <$100).

15 16

Frequency distribution: summary Guidelines for forming class interval

1. Simple frequency distribution: easy task and can either do

manually or rely on statistical software
2. Grouped frequency distribution: more difficult. The
hardest task is to decide the number of classes and class
width or class intervals. Obs in one class should be
homogenous in terms of characteristics. The more you
work on it, the more reasonable classes’ number and size
you decide
3. The upper value of the previous class should not coincide
with the lower value of the following class to make sure
each value should only be in one class.

17 18

3
 Class midpoint, cumulative, percentage, and Class midpoint, cumulative, percentage, and
cumulative percentage frequency distribution cumulative percentage frequency distribution

Wages (class Class Number of Cumulative Percentage Cumulative • Class midpoint: the average
interval) midpoint people frequency frequency percentage
(frequency) frequency • Cumulative frequency: running total of frequencies
< $100 50 2 2 6.7 6.7 through the classes of a FT
$100 – < $200 150 5 7 16.7 23.3
$200 – <$300 250 8 15 26.7 50.0
• Percentage (relative) frequency: proportion of a
$300 – <$400 350 9 24 30.0 80.0 frequency of a class on total frequencies.
$400 – <$500 450 5 29 16.7 96.7 • Cumulative percentage frequency: similar to
$500 – <$600 550 1 30 3.3 100.0
cumulative frequency but in percentage
Total 30

19 20

See how the figures tell you

Practice with SPSS https://edition.cnn.com/videos/politics/2020

/08/04/president-trump-axios-interview-
vpx.cnn

21 22

Charts Bar and pie charts

• Back to the UNSW survey example, create a bar and pie
charts
• Tools for qualitative and discrete data: • Reduce numbers of classes for easily visual look
• Simple bar charts
Number of students Percentage
• Pie charts Nationality (frequency) frequency
Australia & NZ 180 26.24%
• Tools for continuous data:
China 120 17.49%
• Histograms South East Asia 227 33.09%
• Boxplots (discussed in lecture 4) India 11 1.60%
USA & Canada 14 2.04%
UK & Ireland 35 5.10%
Other Europe 42 6.12%
Rest of the world 57 8.31%
Total 686 100.00%
23 24

4
 Bar charts: example of UNSW Pie charts: example of UNSW

Percentage of inter.students at UNSW

Number of inter. students at UNSW 8.31%
6.12%
250
5.10%
200 26.24%
2.04%
Frequency

150 1.60%

100
17.49%
50 33.09%

0
Australia China South India USA & UK & Other Rest of
Australia & NZ China South East Asia India
& NZ East Asia Canada Ireland Europe the world
USA & Canada UK & Ireland Other Europe Rest of the world

25 26

More on bar and pie charts More on bar and pie charts
- Should we use bar or pie? - Should we use bar or pie?

Number of inter. students at UNSW Percentage of inter.students at UNSW

8.31%
6.12%
250
5.10%
200 26.24%
2.04%
F req u en cy

150 1.60%

100
17.49%
33.09%
50

0
Australia China South India USA & UK & Other Rest of Australia & NZ China South East Asia India
& NZ East Asia Canada Ireland Europe the world USA & Canada UK & Ireland Other Europe Rest of the world

27

Notes Histograms

 Choose charts that present information most  Raw data => frequency table => histograms
effectively (‘Learning by doing’)  A histogram looks like a bar charts except that
the bars are joined together
 Practice with SPSS
 Two types of histograms:
 Equal-width histogram
 Unequal-width histogram

29 30

5
 Equal-width histogram Equal-width histogram with normal curve
 All bars have the same width (the same class intervals)
 The height of each bar represents the frequency or
percentage frequency of the class intervals
 Using raw data in the example 4, draw a histogram
representing wages

31

Shapes of histograms – positive skew (long tail

Shapes of Histograms - symmetric
to right)

H i s togr a m of P os itiv e s k e w
Histogr a m of S y mme tr ic
35
50

30
40

25
30
Frequency

Frequency

20

20
15

10 10

5
0
-2.4 -1.6 -0.8 0.0 0.8 1.6 2.4
Sy mme t r ic 0
0 .0 1.5 3.0 4.5 6.0 7.5
Po s it iv e s ke w

33 34

Shapes of histograms – negative skew (long tail

to left) Shapes of histograms - bimodal

Histogram of N egativ e skew Histogram of Bimodal

35 25

30
20
25

15
Frequency
Frequency

20

15 10

10
5
5

0
0 -1.5 0.0 1.5 3.0 4.5 6.0
3.0 4.5 6.0 7.5 9.0 Bimodal
Nega t iv e ske w

35 36

6
 Histogram terms Histograms of COVID19 in the world
• Modal class – class with highest number of
• https://covid19.who.int/?gclid=EAIaIQobChMI
observations
8a‐
• Uni-modal, bi-modal, tri-modal, multi-modal
unPCH6wIVix0rCh3tQAogEAAYASAAEgJb5_D_
• Skewness, symmetry
BwE
• Relative frequency histogram: replace frequency
for each class by • Access data: 7/8/2020
class frequency/total number of obs.

37 38

Flattening COVID19 curve in Korea COVID19 curve in Vietnam

39 40

Distribution of national HS exam scores 2018

Uni entrance exam

41

7
Distribution of national HS exam scores 2018 Distribution of national HS exam scores 2018

Distribution of national HS exam scores 2018 Ogive

Instead of presenting cumulative percentage freq in the
FT, you can draw a graph.

46

Practice with SPSS Bivariate distribution

47 48

8
Investigating the relationship between variables Cross-table
• Methods: • Cross-table is used to investigate the relationship
– Table: Cross-table b/w two categorical vars or discrete variables with
– Charts: few values.
o Multiple bar chart • Note:
o Scatterplot (mentioned in lecture 8)
– Need to identify dependent and independent variables.
– Know how to calculate row and column percentages
– Rule of thumb: independent var in row and dependent
var in column

50

Cross-table Multiple bar chart

• EX: use gss.sav data file to explore the relationship • We can use multiple bar chart to explore the
b/w internet use and degree relationship b/w variables.
• The skill is to know how to draw chart
• EX: use gss.sav data file to explore the relationship
b/w internet use, age, and degree

51 52

Multiple bar chat Summary

Here you are
Univariate distribution
• Table: Frequency distribution
- Simple frequency table
- Grouped frequency table
• Charts
- Bar and pie charts
- Histograms
Bivariate distribution

53 54