An Overview of Statistical Issues (and Opportunities) in Studying Gun Violence

• Activity Number: 255 - Data and Challenges for Unraveling Gun Violence
• Type: Invited
• Date/Time: Tuesday, August 4, 2020 : 1:00 PM to 2:50 PM
• Sponsor: Social Statistics Section
• Author(s): Elizabeth Stuart*
• Companies: Johns Hopkins Bloomberg School of Public Health
• Keywords: gun violence; interrupted time series; non-experimental studies; policy evaluation; program evaluation

Abstract

Gun violence is one of the largest public health problems in the United States, with nearly 40,000 deaths from guns in 2017. Relatively little is known about the causes of gun violence or what strategies are effective at reducing it. This talk will give a broad overview of the state of research related to gun violence, including the epidemiology of gun violence, strategies for evaluating policing strategies, and methods for estimating the effects of state and local policies such as local initiatives to reduce violence and state policies regarding background checks or purchaser licensing requirements. The talk will also highlight some of the many open statistical questions in the field, including regarding measurement challenges (including small area estimation challenges, lack of detailed data at the federal level) and policy evaluation challenges (such as delayed effects, individual states implementing policies at different times, and the multitude of factors influencing gun violence). A key goal will be to help move towards a cadre of statisticians who know enough of the scientific content to be able to contribute meaningfully to the scientific literature on gun violence.