Widget Image
CURRENT ISSUE
ISSUE 00
SUPPORT US
PURCHASE PRINT
Follow us:
Saturday / April 10.
  • No products in the cart.

The Data Visualizations Effect

[IMAGE: GETTY IMAGES]

We tend to believe what numbers say, but just because they are on a chart, that does not make them true. Numbers themselves do not lie, but how we represent them can be really misleading. A chart’s purpose is usually to help you properly interpret data. But sometimes, it does just the opposite.

If you want to detect a cheating chart, It helps to know the kinds of tricks that Data Visualizations can try to pull. Here are six.

 

Truncated Y-Axis

One of the easiest ways to misrepresent your data is by messing with the y-axis of a bar graph, line graph, or scatter plot. In most cases, the y-axis ranges from 0 to a maximum value that encompasses the range of the data. However, sometimes we change the range to better highlight the differences. Taken to an extreme, this technique can make differences in data seem much larger than they are.

 

Broken scales

This is probably the most common way graphics lie, whether intentional or not. Something that changes by 0.1 percent over 10 years and something that changes by 1,000 percent in one year can look exactly the same depending on the scale, or range of values used on the chart. It gets worse when we compare two different elements. In this case, we are making unfair comparisons.

 

Two different scales for comparison

Is 170 pounds more or less than 5 feet 8 inches? The question has no answer because we are talking about two unrelated units, although they speak about related fields. Still, many charts draw these kind of correlations.

 

Puzzling Perspective

Human vision is not very good at interpreting the third dimension. When confronted with a 3D chart, we assume that more colour indicates a greater amount. So, when more pixels are used to represent one slice of a pie chart, the slice appears more significant. That is why we can assign a greater value to foreground slices in 3D pie charts.

 

Biased sampling

This involves polling a non-representative group. For example, a survey that finds “41% of retail bank customers would use mobile banking if it were available,” becomes meaningless when you find out the survey only polled people on their mobile

devices.

 

Small sample sizes

Picking an adequate sample size is part science and part art, but sweeping statements, like “14% of companies plan to deploy cloud-based email this year” becomes suspect when the sample size is 24 companies. Another example of this kind of ‘statistics gone wild’ phenomenon was a “study” conducted by HP that found excessive email usage reduces a person’s IQ by 10 points. 

 

Of course, there are many more ways to lie with charts some subtle, some not just as there are ways to mislead with words and pictures. The biggest enemies of chart cheats are context, analysis, and common sense. Try to apply those next time you see some “shocking truth” in the form of a chart.

Written by

Amir Arres has been the Editor in Chief of Dataism since November 2015. He directs its strategy and development. He has a background in Data Analysis and a BA in Business Decision Making. Amir is interested in how new thinking from Big Data challenges conventional ways of understanding knowledge and culture. His vision for Dataism is to create a sanctuary online for bold and nuanced ideas.