 |
In the September 2005, edition of SIAM News (Volume 38 / Number 7) Lawrence Hubert (UIUC/Psych&Statistics) and Douglas Steinley (UMC/Psych) do a bit of statistical analysis on the Supreme Court. Using the dissimilarity matrix shown in Figure 1, originally published by the New York Times on July 2nd of 2005, they go on to analyze some correlations of the Supreme Court justices. This data set indicates how often justices disagree on non-unanimous cases. This can be viewed as a distance measure and points can be fit appropriately.
A bar chart representing an equivalent (univariate) solution to that provided by Puberty and Steinley is shown in Figure 2. This provides the classic liberal-conservative ordering presented by the Times.
Though Hubert and Steinley do not look at a 2-D correlation, I did, and those results are shown in Figure 3. This brings out some interesting patterns. Though, O'Connor, Renquist and Kennedy all fall into more or less the same place on the 1-D axis, Kennedy and O'Connor have rather divergent opinions, which the 2-D axis picks up. Likewise, the distance of Breyer and Stevens from the other ``liberal'' judges (Ginsberg and Souter), and for that matter each other, is also well-captured in the 2-D plot. I hope you all enjoyed the fun with statistics!
This document was generated using the LaTeX2HTML translator Version 2002-2-1 (1.70)
Copyright © 1993, 1994, 1995, 1996,
Nikos Drakos,
Computer Based Learning Unit, University of Leeds.
Copyright © 1997, 1998, 1999,
Ross Moore,
Mathematics Department, Macquarie University, Sydney.
The command line arguments were:
latex2html -nonavigation -title 'Supreme Court Statistics' -split 0 supreme_court.tex
The translation was initiated by Chris Siefert on 2005-09-07
