The UnAustralian

Tuesday, August 12, 2003
Cherry Picking

One of the common complaints about Bjorn Lomborg's The Skeptical Environmentalist is that it cherry picks what data it presents. This is pretty high up on the list of scientific sins, however, in the real world (whatever that is) it's often hard (well I find it hard) to get across what it actually means.

Luckily, Tim Lambert, has an excellent example of cherry picking, by one of the American Enterprise Institute's finest - John Lott.

In this editorial, Lott claims that:

Crime has risen significantly since the gun ban went into effect. In the five years before Washington's ban in 1976, the murder rate fell from 37 to 27 per 100,000. In the five years after it went into effect, the murder rate rose back up to 35. In fact, the murder rate after 1976 has never fallen back to what it was in 1976. Robberies and overall violent crime changed just as dramatically. Robberies fell from 1,514 to 1,003 per 100,000 and then rose by over 63 percent, up to 1,635.

These statistics, are quite useful for those who feel that global warming has been grossly exaggerated by the IPCC gun control laws increase crime rates (sorry, getting mixed up here).

However, what happens if we look at a graph of crime rates before and after the ban. Tim Lambert has done it for us, and it's quite interesting. A quick eyeball of the graph revels two features:

* that crime rates vary considerable year to year, and
* that the picture of Washington crime rates that Lott (and co-author Lehrer) present is not representative
of reality).

Update: Link fixed. Hopefully.
| 8:04 PM