http://aje.oxfordjournals.org/content/160/10/929.full
snip
To address these limitations, previous researchers have used case-control study methodology to evaluate the relation between gun ownership and risk of a violent death in the home. For example, Kellermann et al. (13, 14) examined the relation between gun ownership and injury outcomes. After they controlled for a number of potentially confounding factors, the presence of a gun in the home was associated with a nearly fivefold risk of suicide (adjusted odds ratio = 4.8) (13) and an almost threefold risk of homicide (adjusted odds ratio = 2.7) (14). Other case-control studies have also found an increased risk of suicide for those with firearms in the home, with relative risks ranging from 2.1 to 4.4 (1519).
Some studies have specifically examined the association between purchase of a handgun and risk of a violent death (20, 21). In a case-control study of members of a large health maintenance organization, Cummings et al. (20) found that a history of family handgun purchase was associated with an elevated risk of both homicide and suicide. Wintemute et al. (21) reported similar findings for suicide in a population-based cohort study of persons who had purchased a handgun in California. In both studies, the effects persisted for more than 5 years. However, studies conducted in other countries have failed to find a clear link between access to a firearm and risk of a suicide (22).
Many of the studies conducted to date have been based on small samples and were limited to specific population groups such as adolescents or older adults (1519). Most of the studies have also been limited to a few counties, geographic areas, or states. We know of only two national case-control studies that have examined the relation between access to a firearm and a violent death (23, 24). One study focused on the perpetration of homicide as opposed to victimization and found a relatively weak association (adjusted odds ratio = 1.4) between gun ownership and homicide perpetration (23). The other study focused on victimization and found a strong association for suicide (adjusted odds ratio = 3.4) but a weak association for homicide (adjusted odds ratio = 1.4) (24). In both studies, cases and controls were drawn from different data sources, and neither study was able to control for many of the potential confounders of homicide or suicide.
To evaluate the relation between firearms in the home and violent deaths in the home, we analyzed data from a US mortality follow-back survey. The purpose of our study was twofold: 1) to determine whether having a firearm in the home increases the risk of a homicide or suicide in the home relative to other causes of death in the home, and 2) to determine whether having a firearm in the home increases the risk that a homicide or suicide in the home will be committed with a firearm or by using other means. To our knowledge, this is the first national study to specifically examine the relation between firearms and violent deaths in the home.
more at link...