Worthy of the Times
Nov 21, 2009
Andrew Gelman has put up a great post, discussing how he collaborated with the New York Times editors to transform his chart to a publishable form. Some time ago, there was a discussion here about the publish-worthiness of my charts (actually, the lack thereof), and I explained that to take my charts to that level would require quite a bit of extra work. Gelman speaks here from first-hand experience.
Here are the two versions side-by-side. Readers on the Gelman blog are debating which version is "better" with Gelman himself voting for the revised NYT version:
Let's compile a list of the changes:
- Removed 2000 data and relied on only 2004 data
- Reduced number of groups of senators from 7 to 5 (with a special calling out of Senator Lieberman)
- Re-ordered senators to facilitate classifying into Democrats, Independent, Republicans
- Added annotation explaining the grouping of senators; in particular, qualified why the 49 Democrats and 32 Republicans were set aside
- Removed scale labels on the top of the chart, retaining only the bottom labels
- Vastly increased the area devoted to text labels, which now covered half of the chart
- Added white vertical gridlines
- Instead of coloring the cross marks, colored the background of the chart; introduced the yellow color for Lieberman (which Gelman originally colored blue)
- Removed reference to the national average but explained clearly in the legend that the percentages are relative to the national average.
There are several good features of the original chart that they left unaltered, which should also be duly noted:
- Allowed the positive side of the scale to extend to 10% even though the largest data only reached about 6%. While this creates empty space, it helps readers judge the magnitude of negative numbers relative to positive ones.
- Subdued horizontal gridlines
- Retained the title of the chart (I actually prefer that they use the title to summarize the finding as opposed to the current one which takes a neutral stance.)
- Retained the horizontal scale labels at 5% apart
Good point on plotting all the dots. If we'd thought of that, we would've done it. I was pretty proud of my original idea which was to combine many Dems as one point and many Reps as another, thus showing 100 senators without having to make a graph with 100 lines (that's how the original version looked).
Posted by: Andrew Gelman | Nov 22, 2009 at 01:16 PM
Andrew: I suspect that your original idea would work better than my suggestion for the mass audience. Statisticians would probably want to see all the data - and dare I say it, how about replacing the averages with boxplots?
Posted by: Kaiser | Nov 23, 2009 at 08:45 PM
on http://www.hichert.com/de/consulting/managementberichte/78-diagrammstrip ( http://www.hichert.com/downloads/newsletter/Chart_Strip_a.pdf )
you can follow a similar dicussion and download a chart-strip dealing with those issues referring "better" charts
Posted by: Ulrich Seidl | Nov 26, 2009 at 12:10 PM