« Oil spills bring out the worst | Main | Off-topic: World cup thoughts »


Peter H



Have you tried doing this in Protovis?


Nice post, some points to add:

  1. With "only" 11 variables and some dozens of observations the SPLOM does still work reasonable well. For 20 variables and some hundreds of cases this plot will fail.
  2. The ellipses help a lot in judging the correlations, but do we need a plot if this is essentially all we look at?
  3. Linking cases across the scatterplots will take us to even higher dimensional insights than just 2-d.
  4. Is the data available somewhere? I am keen on looking at the data in Mondrian.
  5. If there is a geographical reference in the data, i.e., the neighborhoods, we should link the map with the data. This will be far more powerful than any analysis which ignores this aspect.
But the important point is that you actually collected real data and addressed a real problem!

Mike Lawrence

Check out the "ezCor" function in the "ez" package for R. It plots something similar, but with additional features such as univariate densities, correlation coefficients, etc.



Verify your Comment

Previewing your Comment

This is only a preview. Your comment has not yet been posted.

Your comment could not be posted. Error type:
Your comment has been posted. Post another comment

The letters and numbers you entered did not match the image. Please try again.

As a final step before posting your comment, enter the letters and numbers you see in the image below. This prevents automated programs from posting comments.

Having trouble reading this image? View an alternate.


Post a comment

Your Information

(Name is required. Email address will not be displayed with the comment.)

Marketing analytics and data visualization expert. Author and Speaker. Currently at Vimeo and NYU. See my full bio.

Book Blog

Link to junkcharts

Graphics design by Amanda Lee

The Read

Good Books

Keep in Touch

follow me on Twitter