Notable also is that, within Democrats, there seems to be a moderate correlation between social scores and economic scores.

- There is a division between Dem and Reps; I don't see an internal division within either Dems or Reps. Although the range of social scores is ~25% larger within Dems than within Reps, the range of economic scores within Reps is ~33% larger than within Dems.

- Although the range for the social scale is larger, it has been re-scaled (see http://www.stat.columbia.edu/~cook/
movabletype/archives/2008/07/more_info_on_th.html
). Assuming that the re-scaling is related to the variability (which it usually is), then we might infer that there is more relative variability in the social scale (which, in fact, is obvious from the plot), but it says nothing about the range. FWIW, the social score is calculated from 13 questions, and the economic score from 10.

- The observation that the points appear to be 45 degree line overlaid onto the plot is incidental to any correlation; correlation is scale (and location) invariant, that is, the correlation between 1,2,...,10 and 1010,1020,...,1100 is exactly the same as the correlation between 1,2,...,10 and 1,2,...,10.

Pretty graph, but the process used to collect the data is completely unclear and not reproducible.
Would be great to get the details here, otherwise it looks a bit like the self fulfilling prophecies - which is still good academic practice ...

DavidS: thanks for the additional comments. You're right about the 45-deg line; I even pointed out that the two scales were not the same so it's any positive slope line

Martin: if you follow the link in DavidS's post, you will see a fuller explanation of how the ratings were derived (from survey data)

Kaiser,

thanks for pointing to David's link - that explains a bit more, but does not really make me more comfortable with the data.
The way the survey was constructed and conducted may influence the results extremely - at least it has a good leverage on how strongly you may separate the two clusters.

You're using averages though, and that has a clustering effect which gives the impression that there are NO voters that fall in the middle (of which there are many). It would be interesting to somehow rate the people that voted democrats in one elections and then republican in the next (or vice versa). THAT would tell you something.

I recently did some analysis of the General Social Survey. There is a set of the GSS that splits into two very well-defined clusters as well. See my demonstration here: http://orbitalteapot.blogspot.com/2008/05/best-basis-some-gss-exploration.html

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.

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

## NEW BOOTCAMP

See our curriculum, instructors. Apply.
Marketing analytics and data visualization expert. Author and Speaker. Currently at Columbia. See my full bio.

## Book Blog

Graphics design by Amanda Lee