Professional Documents
Culture Documents
APPLICATION (QHO430)
Create tables that convey the information necessary for the viewer to
understand your data.
Choose graph-types that are appropriate for your data.
Produce PivotTables and their appropriate Graphs
Introduction
So, you have data….
The human brain finds it difficult to make sense of even a modest quantity of raw
data. Once the data is properly organised and presented, a surprising amount of
information can be derived from it.
Data visualization is an
interdisciplinary field that
deals with the graphic
representation of data. It is a
particularly efficient way of
communicating when the
data is numerous as for
example a time series
Presentation of Data
Tables
Pie charts In this section, we’re
going to go through a
Bar charts few ways of displaying
Histograms the raw data using
graphical presentation
Boxplots
Time Series Graphs
Scatterplots
Normal Probability Plot
Survival Plot etc.
Narrative format
“Although in 2014 much the larger part of our profits was generated by the
heavy duty ‘HailGood’ range, which contributed £700,000 to a total profit
before tax of £900,000, the policy of diversifying our retail outlets has
altered this situation. In 2015 profits from ‘HailGood’ sales had increased to
£820,000, but those from our lighter ‘RainGood’ range had gone up from
£200,000 to £460,000 over the same period. By 2016 this trend was even
more pronounced, with ‘RainGood’ sales accounting for £680,000 out of a
total profit of £1,610,000.”
All figures in £0,000s. Bracketed figures are per cent of year’s total.
(Source: Company annual reports)
Presenting data in table
Table *: Before-tax profit breakdown of ‘WeatherGood’ for the past three years:
Year HailGood RainGood Total
2014 70 20 90
2015 82 46 128
2016 93 68 161
All figures in £0,000s. Bracketed figures are per cent of year’s total.
(Source: Company annual reports)
Presenting data in table
Figure *: Before-tax profit breakdown of ‘WeatherGood’ for the past three years:
Narrative Format: Revisited
Chart Wizard
Select CHART under the INSERT menu to access the Chart Wizard.
Select the required graph type.
Input the required values and titles.
Specify whether the chart is to appear in the same worksheet as the
data or in a new worksheet.
It is possible to edit the graph further once you have exited the
wizard.
Pie Charts
Used to represent qualitative or discrete data in the form of
frequencies.
The pie (circle) represents the total count.
The size of the angle of each slice represents the relative
frequency within each category.
The pie chart works well with up to 7 categories.
Pie Charts Example 1
Company Part
Company A 15%
Company B 12%
Company C 17%
Company D 18%
Company E 21%
Company F 3%
Company G 4%
Company H 2%
Company I 3%
Other 5%
Total 100%
For example, if you have several companies that
operate on the market, you can represent a part of
every company on the market as a slice.
Pie Charts: Example 2
Set up a column containing the (upper) class limits. This is called the ‘bin
range’.
Select the DATA ANALYSIS option in the DATA section of the Ribbon menu.
If this option does not appear, ensure the Analysis Tool-Pak ADD-INS have
been installed.
Select HISTOGRAM. In the dialog box specify the data range, bin range and
output option.
Use intervals (bin range) of the same width;
Click on a bar to open ‘Format Data Series’; in the Series Options dialogue box
use the Gap Width slider to remove the gaps between the bars.
Histogram: Example Data
Exam Marks Frequency Cumulative %
Maybe if we’ve just
<40 3 5%
returned to Exam Marks
40-49 11 23% data to show how to do
50-59 18 53% histogram in Excel, then we
60-69 19 85% probably don’t need this
70-79 7 97% slide (and maybe next one
80-89 2 100% – tidy up exam marks
90+ 0 100% histogram instead).
Histogram
Frequency Polygons
If you join up the mid-points at the top of each bar, you get a
frequency polygon.
It is possible to construct a frequency polygon using the line
graph command.
If you wish to compare two or more bar charts or histograms
on the same graph, it is usually better to draw the frequency
polygon for each graph.
Consider plotting percentages if the totals are very different.
Frequency Polygons
Shapes
Bar charts, histograms and frequency polygons help to reveal the shape of
the underlying distribution.
Bar charts, histograms and frequency
polygons help to show the shape of
the underlying distribution. Is it
symmetrical like the middle diagram
or skewed like the other two, either
with some very low values or some
very high numbers.
You can see how the mean and
median are affected by skewed data.
Scatterplot
Y-axis - Dependent variable. The variable we are trying to explain.
What you want to predict.
When the data is in the form of a time series, a line graph can
be a useful means of showing any pattern or trend in the data.
Time Series Graph
Another graph that you might
come across is a time series plot. A
time is series is when we measure
the same variable at regular
intervals over time. It’s easiest to
interpret a time series pattern
when we look at a graph.
Box Plot
A box and whisker plot—also called a
box plot—displays the five-number
summary of a set of data. The five-
number summary is the minimum, first
quartile, median, third quartile, and
maximum. In a box plot, we draw a box
from the first quartile to the third
quartile. A vertical line goes through
the box at the median
Good Graphs