Fact: This “study”1has multiple defects which, when corrected, reverse the results. Some of the defects of this study include:
- Exclusion of the District of Columbia, a high crime city
- Use of other crime rates to indirectly explain homicide rates
- Use of purely cross-sectional data that never allows control variable analysis
- Data from different years is used without any explanation (unemployment rate from 2000 to explain the homicide rate from 2001 to 2003, etc.).
This is an excerpt from “Gun Facts” by Guy Smith, available free from http://www.gunfacts.info
- Matthew Miller, David Hemenwaya, Deborah Azrael, “State-level homicide victimization rates in the US in relation to survey measures of household firearm ownership, 2001–2003”, Harvard School of Public Health, October27, 2006 ↩
on Jan 9th, 2009 at 8:41 am
Good writing. Keep up the good work. I just added your RSS feed my Google News Reader..
Matt Hanson