« Narratives | Main | Who works the hardest? II »


Mike Anderson

How about clustering on slope, rather than level? I see two or three very different clusters in that case...


Here's a version that shows relative rankings in 1990, 2004, and the percent change:

Andrew Gelman

With only 2 time points, why not do a scatterplot?



Beat you to it.


Robert just always have a plotting program nearby. Usually for bivariate data, I'd prefer a scatter plot. But when I look at Robert's plot here, the data is correlated in such a way that nothing stands out. The between-country variations appear to be much larger than the within-country variations.

Robert A.

I've written some SAS/Graph code to produce a chart like the oririginal bar chart, if anyone would like to grab a copy and experiment with it ...


The comments to this entry are closed.


Link to Principal Analytics Prep

See our curriculum, instructors. Apply.
Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR.

See my Youtube and Flickr.

Book Blog

Link to junkcharts

Graphics design by Amanda Lee

The Read

Keep in Touch

follow me on Twitter