To: Suma who wrote (303 ) 6/9/2008 11:34:52 AM From: TimF Respond to of 3816 While there appears to be a direct correlation between gun-ownership rates and the number of gun-related deaths I've already commented about this withing the US, now for a response to international comparisons. -------- Is Gun Ownership Correlated with Violent Deaths? In 1993 a Swiss professor, Martin Killias, published a study of 18 countries concerning gun ownership, homicide and suicide. He in part concluded there was a weak correlation between total homicide and gun ownership. For a partial criticism of his study see Dunblane Misled where using the countries studied by Killias, these researchers found a much stronger correlation between firearm homicides and car ownership. More seriously, when the United States was included in the Killias study, a stronger correlation between total homicide and gun ownership was found. When two countries were excluded, the U.S. (high gun ownership, high murder rate) and Northern Ireland (low gun ownership, high murder rate) the correlation was marginally significant. Gary Kleck writes, "Contrary to his claim that 'the overall correlation is not contingent upon a few countries with extreme scores on the dependent and independent variable', reanalysis of the data reveals that if one excludes only the United States from the sample there is no significant association between gun ownership and the total homicide rate." (Kleck, Targeting Guns: Firearms and Their Control, p 253. Walter de Gruyter, Inc. New York, 1997.) Kleck concludes that "the homicide-guns study was not international at all, but merely reflected the unique status of the United States as a high-gun ownership/high-violence nation...Since the positive association Killias observed was entirely dependent on the U.S. case, where self-defense is a common reason for gun ownership, this supports the conclusion that the association was attributable to the impact of the homicide rates on gun levels." Using homicide and suicide data from a larger sample of countries, 35, (International Journal of Epidemiology 1998:27:216), Kleck found "no significant (at the 5% level) association between gun ownership levels and the total homicide rate in the largest sample of nations available to study this topic. (Associations with the total suicide rate were even weaker.)" (Targeting Guns, p 254.) A more recent study, by Killias, concludes "no significant correlations with toal suicide or homicide rates were found, leaving open the question of possible substitution effects." This article by Rutgers University professor Dr. Goertzel offers sound advice regarding statistical analysis: "When presented with an econometric model, consumers should insist on evidence that it can predict trends in data other than the data used to create it. Models that fail this test are junk science, no matter how complex the analysis." guncite.com ------ I would also add that the US has more knife homicides that most other developed countries. The easier availability of firearms would seem to decrease the number of knife homicides (because a gun is generally a superior substitute). This seems to indicate that Americans are more violent, not that people with more guns are more violent.