States With Higher Levels of Gun Ownership Have Higher Homicide Rates
January 11, 2007
Boston, MA — Firearms are used to kill two out of every three homicide victims in America. In the first nationally representative study to examine the relationship between survey measures of household firearm ownership and state level rates of homicide, researchers at the Harvard Injury Control Research Center found that homicide rates among children, and among women and men of all ages, are higher in states where more households have guns. The study appears in the February 2007 issue of Social Science and Medicine. http://dx.doi.org/10.1016/j.socscimed.2006.09.024
Analyses that controlled for several measures of resource deprivation, urbanization, aggravated assault, robbery, unemployment, and alcohol consumption found that states with higher rates of household firearm ownership had significantly higher homicide victimization rates for children, and for women and men.
Miller et al., 2007 is locked up behind a pay wall ($35.95), so I don’t know how they controlled the data to assert “that states with higher rates of household firearm ownership had significantly higher homicide victimization rates;” however the un-bastardized data show the opposite relationship.
This is Figure 1 from Miller et al., 2007…
It appears that they obtained the positive correlation between guns and murder rate by omitting Washington DC and segregating the States by robbery rates.
That’s kind of like calling this, “global cooling”…
I used the same firearms survey as Miller et al., 2007 and the crime rate data from the US Census Bureau:
- BRFSS Survey Results 2001 for Nationwide Firearms
- United States Census Bureau, 2012 Statistical Abstract, Law Enforcement, Courts, & Prisons: Crimes and Crime Rates, 308 – Crime Rates by State, 2008 and 2009, and by Type, 2009
While the gun ownership data pre-date the crime data by 8 years, it is unlikely that the percentages of households with firearms have changed much since 2001.
Murder, robbery and aggravated assault are all negatively correlated with the percentage of households with firearms…
The correlations are even stronger with logarithmic trend lines…
All three violent crime rates were negatively correlated with gun ownership, particularly robbery (R² = 0.398). A 40% correlation is pretty strong with sociological variables like these.
Murder was weakly correlated…
And aggravated assault was essentially uncorrelated…
In all three cases, Washington DC had the highest crime rate and, by far, the lowest prevalence of armed households. If I exclude “Mordor on the Potomac,” the slopes for murder and aggravated assault become slightly positive, although the R² values are essentially zero. The slope of the robbery rate remains negative and the R² is still fairly significant.