This paper examines the relationship between gun ownership and crime. Previous research has suffered from a lack of reliable data on gun ownership. I exploit a unique data set to reliably estimate annual rates of gun ownership at both the state and the county levels during the past two decades. My findings demonstrate that changes in gun ownership are significantly positively related to changes in the homicide rate, with this relationship driven almost entirely by an impact of gun ownership on murders in which a gun is used. The effect of gun ownership on all other crime categories is much less marked. Recent reductions in the fraction of households owning a gun can explain one‐third of the differential decline in gun homicides relative to nongun homicides since 1993.