Graphs are intended to present information as clearly as possible, and to do that you need to understand the types of graphs you have to choose from, as well as what makes one more suitable for some situations than the alternatives. If you need to use graphs in any setting, you’ll need to familiarize yourself with bar graphs and line graphs in particular, because they’re some of the most commonly used graphs around. Bar graphs use rectangular blocks to represent many different types of data, whereas line graphs use lines and represent trends over time particularly well.
TL;DR (Too Long; Didn't Read)
Bar graphs show data with blocks of different lengths, whereas line graphs show a series of points connected by straight lines. This leads to a very different appearance, but the biggest difference is that bar graphs are more versatile while line graphs are better for showing trends over time or another measure with a logical progression of values (such as distance from a given point). Bar graphs can also show frequency distributions (how often you observe different outcomes) much more effectively than line graphs.
What Is a Bar Graph?
Bar graphs involve rectangular blocks of varying heights, and the height of the block corresponds to the value of the quantity being represented. The vertical axis shows the values – for example, the total number of each type of object counted – and the horizontal axis shows the categories. As a concrete example, if you’re counting the different types of vehicles in a parking lot, the individual blocks could represent cars, vans, motorcycles and jeeps, and their heights could represent how many you counted.
The bars can represent pretty much anything you can fit into categories, though, or even the values of the same quantity at different points in time. The height of the bar could also represent a wide range of things, including counts, total revenues, percentages, frequencies or values in any unit of measurement (e.g., heights, speeds or masses). Bar graphs are incredibly versatile, so anybody dealing with data will undoubtedly use them often.
What Is a Line Graph?
A line graph differs from a bar graph in that you plot individual points on the two axes and join neighboring points up using straight lines. The vertical axis could represent basically anything, but the horizontal axis ordinarily represents time. The continuous line (or lines) implies a trend over time or at least over some quantity that increases sequentially, like distance from a given point. The appearance of line graphs differs in quite an obvious way from bar graphs (because there are only thin lines plotted on the axes rather than large blocks), but the function differs substantially too. Line graphs can also represent trends in numerous quantities over time, by using multiple lines instead of just one.
When to Use a Bar Graph
The versatility of bar graphs means they’re useful in many different situations. However, you need to be able to break your data down into specific categories, or at least be able to group it into categories so each distinct bar has a specific meaning. However, since the vertical axis can represent basically anything, you have a lot of options.
Frequency distributions show one way bar graphs can be used to present data. These distributions tell you how the data collected spreads across different potential values. For example, imagine you are looking at people arriving at school in cars, and in particular, how many people travel in each car. You could create a bar graph with the possible numbers of people (e.g., 1, 2, 3, 4 or 5) along the horizontal axis and the number of times you observed the outcome on the vertical axis. This leads to a distribution of results, with the highest bar corresponding to the most common outcome (for example, three people in the car) and the other, less common results shown as smaller bars around it. This gives a very simple visual interpretation of your data.
Another example would be if you were plotting profits and losses from different departments in a store. You could have a bar for each department, and the profits or losses shown as a bar either extending into the positive vertical axis (for profits) or down into the negative (for losses). You could show a trend over time with bars representing each quarter for the whole store overall. Bar graphs can show trends over time for every department individually too, but this gets difficult to interpret, particularly if any changes are small.
When to Use a Line Graph
Bar graphs can show trends over time (as in the previous example), but line graphs have an advantage in that it’s easier to see small changes on line graphs than bar graphs, and that the line makes the overall trends very clear. They are less versatile than bar graphs, but better for many purposes.
For example, if you wanted to show profit trends for individual departments over time, you could have one line for each department, and the progression from left to right would show how the profit changed in successive quarters. Each line shows the department’s trend, so you can follow each one easily. In a bar graph, you’d have to have a series of groups of blocks, with one individual bar for each department clustered together, and then another set of blocks for the next quarter further down the horizontal axis. Visually following one department’s progression through this can be difficult.
Another example would be plotting students’ results on a series of class tests. If the tests measure similar skills, you would hope to see an improvement with successive tests. This could be shown with the scores on the vertical axis and each test numbered along the horizontal axis. Over time the line linking each student’s results should be seen to trend upwards if his or her ability is improving.
References
About the Author
Lee Johnson is a freelance writer and science enthusiast, with a passion for distilling complex concepts into simple, digestible language. He's written about science for several websites including eHow UK and WiseGeek, mainly covering physics and astronomy. He was also a science blogger for Elements Behavioral Health's blog network for five years. He studied physics at the Open University and graduated in 2018.