Tutorials

Defaults are generalized settings to work with many datasets. This is fine for analysis, but data graphics for presentation benefit from context-specific design.

When you want to focus on the magnitude of differences between low and high values, use visual cues that highlight distance.

Mapping one dot per person, it's all about putting the pieces together.

Moving your data from the digital screen to something more physical isn't as tricky as it seems. Here's how I did it.

Show connections in the circular layout for a more compact presentation.

Make the unit chart less abstract with icons that represent the data, or use this in place of a bar chart.

Also known as waffle charts. Using animated transitions between values, you can allow for comparisons between categories.

The usually abstract, qualitative and sometimes quantitative chart type shows relationships. You can make them in R, if you must.

Combining small multiples with the grid layout can make for an intuitive geographic reference.

For when you want to show or compare several distributions but don't have a lot of space.

Add interaction so that you can show different segments of the data and allow comparisons.

Add the vertices. Connect them with edges. Repeat as necessary.

Also known as a polar plot, it is usually not the better option over a standard line chart, but in select cases the method can be useful to show cyclical patterns.

It's the half cousin of the bubble plot with less overlap and more straight edges.

The histogram is my favorite chart type, but it's unintuitive for many. So I've been using the less accurate but less abstract beeswarm.

When there are too many options or categories, it can be helpful to make the data searchable.

Something of a cross between a reference table and a map, the state grid provides equal space to each state and a semblance of the country to quickly pick out individual states.

Sometimes it's useful to animate the multiple lines instead of showing them all at once.