Category: Visualization

Stephanie Evergreen walks us through an interesting technique for creating dumbbell-style dot plots in Excel:

Ok, babes, prepare to be amazed. It used to be that making this viz was pretty tedious but I’ve recently refined a totally new hack (thanks to a lollipop chart example provided by Sevinc Rende, one of my mentees) that makes this soooooooo easier. It used to be ninja level 9. Now it is ninja level 5, if that.

We will create a dumbbell dot plot out of a stacked bar, where the first stack is composed of our first set of dot values and the second stack is composed of *the difference* between our first and second values (so that it would end at our second values on the x-axis scale). So let’s calculate the difference between the 2020 and 2010 scores.

Read on to see how.

Mike Cisneros takes us through one of the most useful visuals out there:

A typical line graph will have continuous data along both the vertical (y-axis) and horizontal (x-axis) dimensions. The y-axis usually shows the value of whatever variable we are measuring; the x-axis is most often used to show when we measured it, either chronologically or based on some independent variable (e.g., as we rev our old car’s engine, we measure the decibel level at different RPM). 

While some line graphs do not use continuous data on the x-axis (particularly slopegraphs and parallel coordinates diagrams, which are specialized variants of line graphs), what we absolutely can’t use on our x-axis is data that doesn’t have any meaningful relationship among the categories shown. 

Read on for a lot of good information on a workhorse visual.

Stephanie Evergreen shows a couple of ways to visualize multi-select results:

Which means a bar chart, ordered greatest to least, is your alternative. But that can have many variations.

In this example, created by Dr. Sheila B. Robinson, she used 100% stacked bars for each survey item, to indicate that each item could have totaled 100% if all respondents checked that box. This is a nice way to show that, while the response options as a whole can’t add to 100%, each option on its own CAN. Plus, look at the cute icons.

Click through for several alternatives depending upon the story you’re trying to tell.

Stephanie Evergreen shows various ways to visualize ratings data:

Stacked Bars *seem* like a good idea – we show 100%, we can fit more questions and data into a similar amount of space – advantages, right? Except that stacked bars are difficult for people to read. How well can you compare the values of the orange segments? Not so much.

If you are going to use stacked bars, make some helpful formatting tweaks, like smarter color coding and an order from greatest to least.

A lot of this comes down to simplification and reduction of possibilities. Read the whole thing.

Elizabeth Ricks tries the impossible:

A friend called me recently and started our conversation with: “I know you dislike pie charts, but…can you help me create one?” 

Spoiler alert: I don’t hate pie charts. They’ve received a bad rap over the years and with good reason—they are very commonly used when another chart type would be better suited. The appropriate use case for a pie chart is expressing a part-to-whole relationship. Their limitation is that it can be difficult to accurately judge the relative size of and compare the segments. Here are some related articles on our blog: the great pie debate and an updated post on pies. 

Elizabeth does put together the best possible case, but I’m still in favor of burning pie charts to the ground.