From: Eliezer S. Yudkowsky (sentience@pobox.com)
Date: Mon Aug 25 2003 - 11:54:13 MDT
> Others say that theory is refuted by the government's own data. The Justice
> Policy Institute, a research group that favors alternatives to prison,
> pointed out that regions with higher prison expansion rates, such as the
> South and West, experienced more murders in 2002.
Note the comparison of a derivative (the South and West have higher prison
*expansion* rates) with the absolute number of murders, the lack of any
data on statistical significance, and the abject confusion of correlation
with causation. Of course, at least some of this is probably the
reporter's fault.
I'm not taking sides on the particular issue, just getting more and more
annoyed with the total uselessness of all media-reported data.
-- Eliezer S. Yudkowsky http://singinst.org/ Research Fellow, Singularity Institute for Artificial Intelligence
This archive was generated by hypermail 2.1.5 : Mon Aug 25 2003 - 12:11:12 MDT