Related Experiment Video
Updated: Aug 2, 2025

Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
Black Household gun ownership and black suicide rates across U.S. States
David Hemenway1, Deborah Azrael1, Wilson Zhang1
1Harvard TH Chan School of Public Health, 677 Huntington Avenue, Boston, MA 02115 USA.
Introduction:
Ecologic studies have examined the relationship across states between levels of household gun ownership and suicide rates using household gun ownership data from the Behavioral Risk Factor Surveillance System (BFRSS) or proxies. However, no study has examined how race-specific survey-based or proxy measures of gun ownership are related to race-specific suicide rates.
Methods:
We use cross-sectional state-level race-specific data to examine how well various proxies correlate with race-specific BRFSS gun ownership rates. We examine whether BRFSS measures of household gun ownership are correlated with firearm suicide, non-firearm suicide, and total suicide rates, for Black and for White adults, and repeat these assessments with select proxies. The core BRFSS only included gun questions in 2001, 2002, and 2004, but not since; mortality data are collapsed 2001-2010.
Results:
Among a set of proxies, the race-specific fraction of suicides that are firearm suicides (FS/S) is the measure most highly correlated with BRFSS household gun ownership. Across states, White adult BFRSS household gun ownership levels are highly correlated with White adult firearm suicide rates (correlation coefficient .82) and moderately correlated with White overall suicide rates (.63). However, for Black adults, we find that while the state-level Black gun ownership levels are moderately correlated with Black firearm suicide rates (.67)-more strongly for older (.70) than for younger (.47) Black adults-Black BRFSS gun ownership levels are only weakly correlated with Black overall suicide rates (.17) owing to a moderate inverse correlation with Black non-firearm suicide rates (-.45). For Black adults, the relationship between FS/S and suicide is similar to the relation between BRFSS and suicide.
Conclusion:
For White adults, states with higher levels of measured household gun ownership have higher overall suicide rates. This relationship does not hold for Black adults, largely due to a more attenuated correlation between these measures of firearm availability and firearm suicide rates coupled with a more substantial countervailing (inverse) relationship between these measures and non-firearm suicide rates. Future efforts using individual level data might help determine why this puzzling difference exists, especially for young Black adults.
Related Concept Videos
Correlations
Correlation and Causation
Correlation versus Causation
If the dependent variable increases or decreases when the independent variable increases, there is a positive or negative...
Correlation
Two variables, for example, a and b, are said to be positively correlated if both variables move in the same direction. In other words, a positive correlation exists between two variables, a and b, if:
Cause and Effect
Hypothesis Test for Test of Independence
H0: The two variables (factors)...
Self-Presentation: Self-Monitoring and Self-Handicapping

