March 1, 2020
A Guide to Bar Charts
If you’ve ever kept up with the news, you’ve likely stumbled across a bar chart. The ubiquity of bar charts is in part due to their simplicity. While they can be very basic, they’re powerful tools for conveying information about any data set.
Bar charts are often confused with histograms because of the fact they both visualize data using bars. The main difference between a histogram and a bar chart has to do with the kind of data that they display. While histograms display two quantitative variables, bar charts display one or more categorical variables against a quantitative variable.
In the table below, we’ve summarized the main differences between histograms and bar charts by comparing their characteristics.
|Vertical Axis||Quantitative variable||Quantitative variable|
|Horizontal Axis||Quantitative variable||Categorical variable|
|Bars||No space between them||Spaces between them|
|Order of Bars||Order matters||Order doesn’t matter|
In general, there are three types of bar charts, which include:
- Clustered Bar Chart
- Stacked Bar Chart
- 100% Column Bar Chart
All of these bar charts are used for different purposes and each can be constructed either vertically or horizontally.
Clustered bar charts are what you typically think of when bar charts are mentioned. They typically look like the image below.
Looking at this image, we can see that there are categories on the horizontal axis and a quantitative variable on the vertical axis. Sometimes, to better display the data, people construct bar charts horizontally. This looks like the following image.
Stacked bar charts are bar charts that are used when you want to compare the totals and proportions of each categorical variable. They look like the image below.
While it may sound strange, the 100% column bar chart is also an easy bar chart to comprehend. This bar chart is used when you want to compare the proportion of each categorical variable to the total amount. This would look like the image below.
What you may already know is that visualizations can be combined in order to better present information. These types of charts are generally known as combination charts. Bar charts are typically only combined with two other types of charts: line and area charts.
Using fictitious average ages, we can also give information using a combination chart. Using a line chart to convey this information would look like the following.
In the table below, you’ll find a summary of the best time to use each type of chart we’ve reviewed in this section.
|Type of Bar Chart||When to Use It|
|Clustered||Used when wanting to compare totals between different qualitative variables or changes over time|
|Stacked||Used for comparing totals and the different categories within one or more qualitative variables or for changes over time|
|100% Column||Used when wanting to compare the proportions of different categories within one or more qualitative variables or for changes over time|
In general, when constructing any type of chart, there are a couple of general rules you should stick to in order to make sure the information you want to display is as understandable as possible. These best practices can be found in the table below.
|Uses of Bar Charts||Best Practices|
|Constructing Bar Charts||When constructing a bar chart, you can make it easier for readers by: |
|Displaying Bar Charts||When choosing how to display your bar chart, make sure you: |