Descriptive Statistics

Part 1 : Frequency Distributions and

Their Graphs

1
List of symbols used

2
 RAW DATA
ID GENDER COURSE QUIZ SCORE (10%)
1 M BBB 8
2 M BBB 7
3 M BBC 8
4 F BBC 6
5 F BBC 7
6 M BBE 5
7 M BBE 5
8 F BBC 7
9 F BBB 8
10 F BBC 7
11 F BBE 7
12 M BBB 7

3
 Outline

• 2.1 Frequency Distributions and Their Graphs

• 2.2 Measures of Central Tendency

• 2.3 Measures of Variation

4
 Overview

Descriptive Statistics
• Describes the important characteristics of a set of
data.
• Organize, present, and summarize data:
1. Graphically
2. Numerically

5
 Important Characteristics of
Quantitative Data
“Shape, Center, and Spread”
• Center: A representative or average value that
indicates where the middle of the data set is located.

• Variation: A measure of the amount that the values

vary among themselves.

• Distribution: The nature or shape of the distribution

of data (such as bell-shaped, uniform, or skewed).
 “Shape” of Distributions

Symmetric
• Data is symmetric if the left half of its histogram is
roughly a mirror image of its right half.

Skewed
• Data is skewed if it is not symmetric and if it
extends more to one side than the other.

Uniform
• Data is uniform if it is equally distributed (on a
histogram, all the bars are the same height or
approximately the same height).
 The Shape of Distributions
Symmetric Uniform

Skewed left Skewed Right

 Outliers

Outliers
• Unusual data values as compared to the rest of the set.
They may be distinguished by gaps in a histogram.
 Section 2.1
Frequency Distributions
and Their Graphs

10
 Frequency Distributions

Frequency Distribution
• A table that organizes data values into classes or
intervals along with number of values that fall in
each class (frequency, f ).
1. Ungrouped Frequency Distribution – for data
sets with few different values. Each value is in
its own class.

2. Grouped Frequency Distribution: for data sets

with many different values, which are grouped
together in the classes.
 Grouped and Ungrouped
Frequency Distributions

Ungrouped Grouped

Courses Frequency, f Age of Frequency, f

Taken Voters
1 25 18-30 202
2 38 31-42 508
3 217 43-54 620
4 1462 55-66 413
5 932 67-78 158
6 15 78-90 32
 Ungrouped Frequency Distributions:
step by step
1. RAW DATA 2. DEVELOP TABLE 3. FILL IN DATA

Number of Peas in a Pea Peas per Freq,

Pod pod Freq, f Peas per pod f
Sample Size: 50
1 1
5 5 4 6 4
3 7 6 3 5 2 2

6 5 4 5 5 3 5
6 2 3 5 5
4 9
5 5 7 4 3
4 5 4 5 6 5 18

5 1 6 2 6 6 12
6 6 6 6 4
7 3
4 5 4 5 3
5 5 7 6 5
 Graphs of Frequency Distributions:
Frequency Histograms

Frequency Histogram
• A bar graph that represents the frequency distribution.
• The horizontal scale is quantitative and measures the
data values.
• The vertical scale measures the frequencies of the
classes.
• Consecutive bars must touch.

frequency data values

Larson/Farber 4th ed. 14
 Frequency Histogram

Example. Peas per Pod

Number of Peas in a Pod

Peas per pod Freq, f
1 1 20

15

Frequency, f
2 2

3 5 10

4 9 5

5 18
0
6 12 1 2 3 4 5 6 7
Number of Peas
7 3
 Relative Frequency Distributions and
Relative Frequency Histograms
Relative Frequency Distribution
• Shows the portion or percentage of the data that falls
in a particular class.
class frequency f
• relative frequency  
Sample size n

Relative Frequency Histogram

• Has the same shape and the same horizontal scale as
the corresponding frequency histogram.
• The vertical scale measures the relative frequencies,
not frequencies.
16
 Relative Frequency Histogram
Has the same shape and horizontal scale as a
histogram, but the vertical scale is marked with
relative frequencies.
 Grouped Frequency Distributions

Grouped Frequency Distribution

• For data sets with many different values.
• Groups data into 5-20 classes of equal width.

Exam Scores Freq, f Exam Scores Freq, f Exam Scores Freq, f

30-39 30-39 1
40-49 40-49 0
50-59 50-59 4
60-69 60-69 9
70-79 70-79 13
80-89 80-89 10
90-99 90-99 3
Grouped Frequency Distribution Terms

• Lower class limits: are the smallest numbers that

can actually belong to different classes

• Upper class limits: are the largest numbers that can

actually belong to different classes

• Class width: is the difference between two

consecutive lower class limits

19
 Labeling Grouped Frequency
Distributions
• Class midpoints: the value halfway between LCL
and UCL:
(Lower class limit)  (Upper class limit)
2

• Class boundaries: the value halfway between an

UCL and the next LCL
(Upper class limit)  (next Lower class limit)
2
 Constructing a Grouped Frequency
Distribution
1. Determine the range of the data:
 Range = highest data value – lowest data value
 May round up to the next convenient number
2. Decide on the number of classes.
 Usually between 5 and 20; otherwise, it may be
difficult to detect any patterns.
3. Find the class width:
 .class width = range
number of classes

 Round up to the next convenient number.

21
 Constructing a Frequency Distribution
4. Find the class limits.
 Choose the first LCL: use the minimum data
entry or something smaller that is convenient.
 Find the remaining LCLs: add the class width to
the lower limit of the preceding class.
 Find the UCLs: Remember that classes must
cover all data values and cannot overlap.
5. Find the frequencies for each class. (You may add a
tally column first and make a tally mark for each
data value in the class).

22
 4 RULES: Constructing a Frequency
Distribution

1. There should be about 10 class intervals.

2. The width of each interval should be a "simple"
number (2, 5, 10, 20, etc.).
3. The bottom score in each class interval should be a
multiple of the width.
4. All intervals should be the same width.

23
4 RULES: Example

24
 4 RULES: Example
1. We note that the maximum is 94 and the minimum is
53. Thus we have a range of 94 - 53 + 1 = 42 potential
scores.
2. We divide this range into about 10 class intervals (rule
1), each of which is a "simple" number (rule 2). This
leads to 9 intervals with a width of 5 each.
3. We make the bottom interval start at 50 since this is
the first number below the minimum that is a multiple
of the interval width (rule 3).
4. The bottom inteval would be 50-54, the next one 55-
59, etc. This makes all intervals the same width (rule
4). 25
4 RULES: Example

26
 Other Graphs

Besides Histograms, there are other methods of

graphing quantitative data:

• Stem and Leaf Plots

• Dot Plots
• Time Series
 Stem and Leaf Plots
Represents data by separating each data value into
two parts: the stem (such as the leftmost digit) and
the leaf (such as the rightmost digit)

Larson/Farber 4th ed. 28

 Constructing Stem and Leaf Plots

• Split each data value at the same place value to form

the stem and a leaf. (Want 5-20 stems).
• Arrange all possible stems vertically so there are no
missing stems.
• Write each leaf to the right of its stem, in order.
• Create a key to recreate the data.
• Variations of stem plots:
1. Split stems
2. Back to back stem plots.

Larson/Farber 4th ed. 29

 Constructing a Stem-and-Leaf Plot

Include a key to identify

the values of the data.

Larson/Farber 4th ed. 30

 Dot Plots

Dot plot
• Consists of a graph in which each data value is
plotted as a point along a scale of values

Figure 2-5
 Time Series
(Paired data)
Time Series
• Data set is composed of quantitative entries taken at
regular intervals over a period of time.
 e.g., The amount of precipitation measured each
day for one month.
• Use a time series chart to graph.

Quantitative
data time
Larson/Farber 4th ed. 32
 Time-Series Graph

Number of Screens at Drive-In Movies Theaters

Figure 2-8

Ex. www.eia.doe.gov/oil_gas/petroleum/
 Graphing Qualitative Data Sets

Pie Chart
• A circle is divided into sectors
that represent categories.

Pareto Chart
• A vertical bar graph in which the

Frequency
height of each bar represents
frequency or relative frequency.

Categories

Larson/Farber 4th ed. 34

 Constructing a Pie Chart
• Find the total sample size.
• Convert the frequencies to relative frequencies (percent).
Marital Status Frequency,f Relative frequency (%)
(in millions)
55.3
Never Married 55.3  0.25 or 25%
219.7
127.7
Married 127.7 
219.7
13.9
Widowed 13.9 
219.7
22.8
Divorced 22.8 
219.7
Total: 219.7 35
 Constructing Pareto Charts

• Create a bar for each category, where the height of the

bar can represent frequency or relative frequency.
• The bars are often positioned in order of decreasing
height, with the tallest bar positioned at the left.

Figure 2-6
Contoh:

 Seorang petani ingin memahami keadaan berat

padi dari sawah yang baru dituainya. Data dari
tuaian sawahnya adalah seperti berikut:
Berat padi dalam kilogram (kg)
64 64 59 72 71 80
81 67 62 71 85 90
63 69 91 70 89 58
72 63 90 68 82 54
75 61 83 63 81 53
90 72 84 60 64 72
87 73 82 55 59 72
86 75 79 81 58 75
83 74 65 87 81 74
80 70 87 78 88 70
 Taburan kekerapan/frekuensi mengandungi kelas atau kumpulan atau
kadang-kadang dipanggil sebagai kelas interval. Biasanya jumlah
kelas yang digunakan untuk membentuk suatu taburan kekerapan
adalah di antara lima (5) dan sembilan (9). Walau bagaimanapun
anda boleh mengadakan lebih dari itu misalnya 15. Formula berikut
boleh digunakan untuk menganggarkan lebih tepat lagi

k = 1 + 3.3 log N

di mana k adalah bilangan kelas

N jumlah bilangan data/sampel
log N adalah log asas 10

 Histogram adalah geraf bar yang menggambarkan corak sesuatu

taburan kekerapan. Ia menerangkan kekerapan lajur bagi sesuatu
kelas. Berikut ditunjukkan cara mendapatkan histogram dari sampel
berat padi.
 Untuk mendapatkan bilangan kelas bagi 60 sampel berat padi

k = 1 + 3.3 log N
= 1 + 3.3 log 60
= 1.3.3 (1.7782)
= 1 + 5.8681
= 6.8681
 7.0
.

 Oleh itu kita sepatutnya menggunakan 7 kelas untuk

membentuk histogram sampel padi. Julat bagi data padi ialah
(91-55) = 37 unit.
Julat = (maksimum - minimum) + 1

37
Setiap kelas mengandungi  6 unit
7
 Talli untuk kepada
adalah seperti berikut:

Bilangan Kelas Kelas Mengikut Talli Kekerapan

Berat
1 49-55 ||| 3
2 56-62 |||| || 7
3 63-69 |||| |||| 10
4 70-76 |||| |||| |||| | 16
5 77-83 |||| |||| || 12
6 84-90 |||| |||| | 11
7 91-97 | 1
 = 60
Bentuk Histogram Yang di
Lakarkan

20

15

f 10

0
1 2 3 4 5 6 7
Kelas M en giku t Berat
THANK YOU.