I'm not a numbers person by Selena Fisk

Author:Selena Fisk
Language: eng
Format: epub
Publisher: Major Street Publishing
Published: 2022-10-15T00:00:00+00:00

Graphing 101

Before we start talking through the different types of visualisations that you have access to or might develop for yourself, there are a couple of things worth noting. Without an awareness of these factors, you could potentially misread or misunderstand a graphic – leading to incorrect assumptions, and decision-making that is not all that useful or accurate.

The first thing to be aware of is graph structure. Graphs often plot time across the page (on the horizontal/x-axis) and the metric along the vertical/y-axis. This type of graph represents how the metric has performed over time. The reason that time is usually on the horizontal axis is this axis should almost always have an independent variable on it – that is, something that generally continues, regardless of any other factors. Time continues regardless of what your business is doing, so it is usually independent.

The vertical axis usually shows a variable that is dependent on the other variable. For example, we talk about inflation as a percentage, so in an graph that represents inflation, the percentage is the vertical axis and time progresses along the horizontal axis. In a bar graph with categories and frequencies (such as the graphs depicting preferred cola brands we looked at in chapter 1), the horizontal axis is the types or categories being shown, and the vertical axis is the frequency of responses. This is because the number of people represented in each bar depends on the categories that are labelled on the horizontal axis.

Another factor worth being aware of is the way that graphs can be deliberately manipulated to exacerbate the appearance of differences, changes or consistent trends. In chapter 1 we saw, via the preferred cola brand graphs, how axis labels can be manipulated to make the data look better or worse. This type of manipulation can trick the viewer into believing the visual and jumping to conclusions, rather than thinking more deeply about the data itself.

The other factor to be mindful of is inconsistent increases in the scale or measurements on either axis. It is not easy to do this if you’re creating graphs in spreadsheeting programs, but sometimes people do choose to design graphs to emphasise or minimise differences by changing the gaps or value size from one tick mark to the next. For example, if the axis begins at zero and increases in units of five, the axis should continue in units of five all the way along the axis, and each of the increments should be the same length on the axis. There should never be a change in the multiples as the graph progresses – for example, an increase in 5s that jumps to an increase in 15s. There should never be a change in the length between the tick marks, either – it should be consistent throughout.

If you notice issues with axis manipulation, it is important to identify the issue and then question why the person developing the visualisation wanted to manipulate the data in this way. You might want to go back to them and have them change or correct the axis.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.