Scattered Pie’s, Donuts and Bars

When analysing data, we are typically searching for patterns, relationships and outliers. As our minds are geared towards visual perception, we need the aid of visualisation to sift through rows of data and extract the insight data has to offer.

The visualisation we choose can have a direct impact on how we interpret and derive value from data discovery, sometimes we don’t know what type of chart matches the data set we are analysing, so we found a simple formula that can help you get to value faster by asking a few basic questions about your data.

We’ve summarised what to look out for when choosing the right data visualisation.

Vertical Bar Charts

Vertical bar charts are best for comparing means or percentages between 2 to 7 different groups.

Horizontal Bar Charts

The horizontal bar chart is used when comparing the mean or percentages of 8 or more different groups. As with the vertical bar chart, the horizontal bar chart should only be used when comparing categories that are mutually exclusive.

Pie Charts

Pie charts are best used to illustrate a sample break down in a single dimension. In other words, it is best to use pie charts when you want to show differences within groups based on one variable. It is important to remember that pie charts should only be used with a group of categories that combine to make up a whole.

Line, Spline & Area Charts

Line charts are used to illustrate trends over time. This is done most often to measure the long term progression of sales, or any other empirical statistic important to businesses or organizations. It can also be used to compare two different variables over time. When choosing an area chart it’s important that there are not to many series represented as it can clutter the chart.

Scatter Charts

Scatter plots are used to depict how different objects settle around a mean based on 2 to 3 different dimensions. This allows for quick and easy comparisons between competing variables. As a viewer, one can quickly reference the difference between two objects or its relation to the average.

To find out what type of visualisation will match your data, sign up for OQLIS today.