Data Representation of Data
Based on Cambridge International AS & A Level Mathematics:
Probability & Statistics 1
1. Why Do We Represent Data?
Data is just information. We collect it to answer questions and understand
the world. But a big list of numbers is hard to understand. Data
representation means turning that list into charts, graphs, or diagrams
so we can see patterns, trends, and what's "normal" at a glance.
Example: Instead of listing the height of every student in your class
(e.g., 155cm, 160cm, 162cm, 158cm...), you could draw a chart.
This chart would instantly show you the most common height and
how much the heights vary.
2. Types of Data
Not all data is the same. We group it into two main types:
Type Description Examples
- Blood type (A,
B, O, AB)
Data that describes a quality - Favourite colour
Qualitative - Car brand
or category. It is non-
(Categorical)
numerical. - Eye color
(Brown, Blue,
Green)
- Number of pets
- Height
Data that can be counted or - Test score
Quantitative
measured. It is numerical.
- Height of
students in cm
Quantitative data is further split into two types:
Discrete Data: Can only take specific, separate values.
You count them.
o Example: Number of students in a class (You can't have 25.5
students!).
Continuous Data: Can take any value within a range.
You measure them.
o Example: Height (Someone can be 165.1 cm, 165.2 cm, etc.).
It depends on the accuracy of your measuring tool.
3. Ways to Represent Data
a) Stem-and-Leaf Diagrams
Best for small sets of discrete data. It's like a quick histogram that still
shows you every single raw data point.
How it works: The "stem" is the first digit(s) and the "leaf" is the
last digit.
Example: Let's say the ages of people in a room are: 12, 15, 15, 17,
21, 24, 25, 26, 32, 34.
Ste
Leaf
m
255
1
7
145
2
6
3 24
Key: 2 | 1 means 21
From this, we can instantly see that the youngest person is 12, the oldest
is 34, and the most common ages are in the mid-20s.
b) Histograms
Best for continuous data that has been grouped into classes. The area of
each bar represents the frequency, not just the height. This is crucial
when the class widths are different.
How it works:
1. Find the class boundaries (the true limits of each group).
2. Calculate the Frequency Density: Frequency Density =
Frequency / Class Width
3. Plot the bars: X-axis = the measurement, Y-axis = Frequency
Density.
Example: We measure the time (to the nearest minute) 36 people
take to run a race.
Time Frequen
(min) cy
13 4
Time Frequen
(min) cy
14-15 14
16-18 18
First, we find the true class boundaries and calculate Frequency Density:
Class Frequen Frequency
Time (min)
Width cy Density
12.5 ≤ t <
1 4 4÷1=4
13.5
13.5 ≤ t <
2 14 14 ÷ 2 = 7
15.5
15.5 ≤ t <
3 18 18 ÷ 3 = 6
18.5
Now we draw the histogram. The bar for the '14-15' group is the tallest
because it has the highest frequency density, even though it doesn't have
the highest frequency.
[Link]
c) Cumulative Frequency Graphs
Used to find how many values lie below a certain point. It's great for
finding medians and quartiles.
How it works:
1. Create a table of upper class boundaries and a running
total of frequencies (cumulative frequency).
2. Plot the points: X-axis = Upper Boundary, Y-axis =
Cumulative Frequency.
3. Connect the points with a smooth curve or straight lines.
Example: The length of 80 leaves.
Length Frequen Upper Cumulative
(cm) cy Boundary Frequency
1-2 8 < 2.5 8
3-4 20 < 4.5 8 + 20 = 28
5-7 38 < 7.5 28 + 38 = 66
8-9 10 < 9.5 66 + 10 = 76
10-11 4 < 11.5 76 + 4 = 80
We plot the points: (2.5, 8), (4.5, 28), (7.5, 66), (9.5, 76), (11.5, 80).
[Link]
Using the Graph:
To estimate the median, find the value corresponding to half the
total frequency (40). We see it's about 5.7 cm.
To estimate how many leaves are shorter than 3.7 cm, go up from
3.7 on the x-axis to the curve, then across to the y-axis. We see it's
about 12 leaves.
Summary
Method Best For Key Thing to Remember
Stem-and- Small, discrete Shows all the raw data. Ordered
Leaf datasets like a histogram.
Area of the bar represents
Continuous,
Histogram frequency. Use Frequency
grouped data
Density.
Cumulative Finding medians, Shows running total. The curve
Frequency quartiles, tells you how many values
Method Best For Key Thing to Remember
percentiles are below a given point.