Last month, I left things pretty open with a makeover challenge, where participants selected less-than-ideal visuals and reworked them, aiming to improve. Many of the makeovers were various types of graphs reimagined as bar charts. I like a good bar chart. Still, this month, I thought we'd both get more specific in the challenge and focus on a graph type that can sometimes be a good alternative to the basic bar: a dot plot.
The term dot plot (or dot chart) can be used for any graph where dots are used to encode data. While this can lead to a ton of variations, there are two primary different types. The first can be used to show the distribution of data (and tends to works best with small datasets, as datasets grow beeswarms or box & whisker become more common); it's similar to a histogram, but the dots aren't necessarily uniformly spaced along the x-axis. The second—which is what I think of first when I say or hear "dot plot"—if you imagine a horizontal bar chart, this version (sometimes referred to as the Cleveland dot plot) instead of plotting bars, plots a dot where the end of each bar would be. In searching through Andy Kirk's Chartmaker Directory, I also found the connected dot plot, which is the second type described above but with two points for each category, typically connected via a line or shaded area. There are likely additional variations as well.
I welcome you to try out any type of dot plot for this month's challenge. The following focuses on the Cleveland version (including the variation of the connected dot plot), since I have more familiarity and experience with these.
I should probably caveat by saying that I don't use dot plots frequently—that's one of the reasons I'll keep the prelude to this month's challenge short and sweet. In many cases where I try a dot plot as one potential view, I end up preferring one of the alternatives. That said, there are situations where they can work well. They are often lauded for using less ink than the bar chart and from a design standpoint can look cleaner because of this. A potential benefit with the (Cleveland) dot plot is that you can zoom or start your axis at something other than zero. This is a no-no with bars, where we compare numbers both to each other and relative to the baseline. With the dot plot, we focus mainly on the positions of the dots relative to each other (not relative to the baseline, like bars), making starting the axis at something other than zero ok. As another sometimes benefit, dots may lend themselves better to being plotted within a range in a way that's more intuitive or to show multiple series of data without becoming cluttered. Sometimes we simply want to plot categorical data as something other than a bar for various reasons, and the dot plot can be an alternative here.
Here's a dot plot I created as part of a client makeover (in this case we wanted to focus on the top two time items, where the gap is the biggest, and the bottom two spend items where the gap is smallest):
In terms of potential risks or considerations with a dot plot, from my perspective probably the biggest one is that they are less common, which means your audience may not be familiar with them. This isn't necessarily a reason not to use, but be aware any time you show your audience something they aren't familiar with, it means that you introduce a hurdle—you have to get them to pay attention (either to you or the data) long enough to figure out how to read the graph. You can certainly do things with words and color to help make this intuitive. The advice I often give applies here, too: consider what you want your audience to be able to do with the data you are showing, then assess whether the type of graph you're considering—in this case, a dot plot—will help make that easy.
Tactically, when it comes to creating a dot plot, they often start out as another graph type with some formatting applied. Stephanie Evergreen has a nice quick post describing how to create a dot plot from a scatterplot in Excel. Andy Kriebel shows how he created a ranked dot plot using a Gantt chart in Tableau in this tutorial. If you have additional tips or tricks related to dot plots that others can benefit from, please leave a comment on this post to share.
For more on dot plots and additional examples, check out Naomi Robbins' article, this makeover by Stephen Few, or the SWD post novel vs. the boring old bar chart. Again, if you're aware of other resources or examples, please leave a comment on this post.
My challenge to you: find some data of interest that will lend itself well and create a dot plot. DEADLINE: Tuesday, August 7th by midnight PST. Full submission details follow (be sure to email it to us, taking note of specifics below, for inclusion in recap post!). You're also welcome to share at any point on social media using #SWDchallenge.
- Make it. Identify your data and create your visual with the tool of your choice. If you need help finding data, check out this list of publicly available data sources. You're also welcome to use a real work example if you'd like, just please don't share anything confidential.
- Share it. Email your entry to SWDchallenge@storytellingwithdata.com by the deadline. Attach your image as a .PNG. Put any commentary you’d like included in my follow up post in the body of the email (e.g. what tool you used, any notes on your methods or thought process you’d like to share); if there’s a social media profile or blog/site you’d like mentioned, please embed the links directly in your commentary (e.g. Blog | Twitter). If you’re going to write more than a paragraph or so, I encourage you to post it externally and provide a link or summary for inclusion. Feel free to also share on social media at any point using #SWDchallenge.
- The fine print. We reserve the right to post and potentially reuse examples shared.
I look forward to seeing what you come up with! Stay tuned for the recap post in the second half of August. Also check out the #SWDchallenge page for past challenge details and recaps.