Gun Violence Archive

General description

1. Database primary purpose - To provide near-real-time data about the results of gun violence
2. Overall data type - incidents involving guns
3. Dataset type - Cross-sectional
4. Data source - Registry
5. Data level - Incident level
6. Geographic location of the data collection sites - United States
7. Sponsor, manager, or home institution - Gun Violence Archive
8. Date range - 2015 - 2022
9. Geolocation data - Incident state, city, county, address
10. Dates - Incident date
11. Number of records - Gun violence incidents collected from over 7,500 law enforcement, media, government and commercial sources daily
12. Variables that are uniquely present in this dataset - Provide free online public access to accurate information about gun-related violence in the United States

Applicable methods

1. Association methods, such as multivariate linear regression models (1, 2), generalized linear model (3), ANOVA (4), negative binomial regression models (5), Bayesian Poisson models (6)
2. Propensity score (7)
3. Time series (8)
4. Machine learning (9)

High-impact designs

• Measure trends in firearm injuries in children and inflicted by children discharging a firearm during the pandemic and correlated these changes with a rise in firearm acquisition (10)

• Assess changes during the COVID-19 pandemic, when firearm violence increased (11)

• To identify the prevalence of and disparities in past-year exposure to deadly gun violence near adolescents' homes and schools (12)

• Evaluate the National Violent Death Reporting System (NVDRS) as a surveillance system for fatal shootings of civilians by law enforcement in the U.S. (13)

Data dictionary

To access Gun Violence Archive data dictionary, click here

Variable categories

1. Patient demographics (i.e., age group, sex)
2. Incident characteristics (e.g., date, number of injured and killed)

Linkage to other datasets

• Linkages can be established for any dataset that might have geolocation data (i.e., State, county, city, address)