We've often heard the statement that just having a gun in a house makes one 2.7 times more likely to be the victim of gun violence.
The root of this statistic is a 1993 study published in the New England Journal of Medicine by Arthur Kellermann et al
http://content.nejm.org/cgi/content/full/329/15/1084The conclusion reads in part:
Despite the widely held belief that guns are effective for protection, our results suggest that they actually pose a substantial threat to members of the household. People who keep guns in their homes appear to be at greater risk of homicide in the home than people who do not. Most of this risk is due to a substantially greater risk of homicide at the hands of a family member or intimate acquaintance.
Here are the problems that many have noted-
The authors note that "One or more guns were reportedly kept in 45.4 percent of the homes of the case subjects," This implies that no guns were kept in 54.6% of the households. No study was made of how many were killed by guns kept in the home versus those brought in by a perpetrator.
Five years later, Kellerman revised himself (quoting
http://www.guncite.com/gun-control-kellermann-3times.html):
A subsequent study, again by Kellermann, of fatal and non-fatal gunshot woundings, showed that only 14.2% of the shootings involving a gun whose origins were known, involved a gun kept in the home where the shooting occurred. (Kellermann, et. al. 1998. "Injuries and deaths due to firearms in the home." Journal of Trauma 45:263-267) ("The authors reported that among those 438 assaultive gunshot woundings, 49 involved a gun 'kept in the home where the shooting occurred,' 295 involved a gun brought to the scene from elsewhere, and another 94 involved a gun whose origins were not noted by the police
.") (Kleck, Gary. "Can Owning a Gun Really Triple the Owner's Chances of Being Murdered?" Homicide Studies 5 <2001>.) Secondly, no correlation was made between "independent" factors that actually may have been factors related to each other- they treated illicit drug use, having an arrest record, living alone or not, renting, having a gun, and a history of domestic abuse as independent variables without any relationship to each other. No collateral multivariate analysis was performed. The correlation to each control was not predicated on other factors, just gun ownership. They gave the same weight to a gun death in a household with someone with a previous arrest as to a gun death in a household where an intruder brought their own gun to a home invasion and shot the occupant (each weighting was independent, not cumulative). No correlation was explored for
similar situations with the only difference being gun ownership.
Thirdly, there were significant differences between the study participants and the control. There was a 30% difference between home ownership vs renting between subjects and control, and a 15% difference in living alone or not. Only 48% of the control subjects were interviewed in person. Never mind that there were more users of illicit drugs, alcoholics, and persons with a history of violence in the households of the case subjects than in the households of the controls.
Thirdly, correlation doesn't equate to causation. They state in one place, "keeping a gun in the home was strongly and independently associated with an increased risk of homicide". "Associated with", not "causally related to". The possibility of why a gun was kept in the home was not explored nor accounted for- so a person who lives in a high crime neighborhood who may _already_ be at higher risk of homicide death was treated the same as a person shot in a "nice" neighborhood.
Further reading (some are related to Kellermann's previous work on the subject, just to show how tortured his conclusions are):
http://www.nationalreview.com/kopel/kopel013101.shtmlhttp://guncite.com/gun-control-kellermann-3times.htmlhttp://www.reason.com/news/show/30225.htmlhttp://www.guncite.com/journals/tennmed.htmlhttp://www.guncite.com/kleckjama01.html -- this one is an especially good article published in the Journal of the American Medical Association
quoting the above:
This association was at least partly attributable to confounding factors that are known to be strongly associated with both gun ownership and homicide victimization, such as dealing in illicit drugs (but not drug use) and membership in a street gang. Either of these confounding factors alone is associated strongly enough with gun ownership and homicide victimization to produce a spurious odds ratio of 2.8,<14> and neither factor was controlled by the researchers. Indeed, most factors that increase the risk of homicide victimization in a way that is evident to the subjects are likely to also motivate some of them to acquire a gun for self-protection.<15> Thus, a positive gun-homicide association is expected even if gun possession had no impact whatsoever on homicide risk.