« Largest ever difference between 328 and 327 spotted in New York City | Main | Taking pages from Gelman »


Jon Peltier

Amazing how the 2003 outlier distorts the entire chart.


In the cleaned up version, the vertical scale should be consistent moneys, instead of just ranking. Did the world series winner out-spend the loser by $1 or by $100 million?

I think that "pretty" and "elegant", at least when it comes to statistics, should start with an image that is instantly understandable. You're exactly right here in that the original is bizarrely difficult to parse.


I agree that those are not pretty pictures! For me, a pretty picture when it comes to data visualization is something that is both aesthetically pleasing and allows for straightforward information discovery. I recently blogged on a visual I would consider to be a very pretty picture - more here: http://www.storytellingwithdata.com/2011/07/breathtaking-data-art.html

I enjoy your blog!


I think you might actually find the data surprisingly difficult to work with. One of my first dashboard projects attempted the same thing using the data that can be found here:

(it's basically my permanent dummy data for all my learnin')

Here's something that bugs me about this data. The biggest outlier there are the Yankees. They outspend the next highest team by quite a bit. If you're talking about highest salary and best performing teams, to me, that feature has to be visible on any chart.


I completely agree -- that NYT chart is rubbish! I'm glad I stumbled on this post to see somebody correct that visual insanity.

I could have saved myself a few long seconds of quizzical/befuddled staring by simply skipping to your version -- it's much better.

The comments to this entry are closed.

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