Predictors of firearm violence in urban communities: A machine-learning approach

Dana E. Goin, Kara Rudolph, Jennifer Ahern

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Interpersonal firearm violence is a leading cause of death and injuries in the United States. Identifying community characteristics associated with firearm violence is important to improve confounder selection and control in health research, to better understand community-level factors that are associated with firearm violence, and to enhance community surveillance and control of firearm violence. The objective of this research was to use machine learning to identify an optimal set of predictors for urban interpersonal firearm violence rates using a broad set of community characteristics. The final list of 18 predictive covariates explain 77.8% of the variance in firearm violence rates, and are publicly available, facilitating their inclusion in analyses relating violence and health. This list includes the black isolation and segregation indices, rates of educational attainment, marital status, indicators of wealth and poverty, longitude, latitude, and temperature.

Original languageEnglish (US)
Pages (from-to)61-67
Number of pages7
JournalHealth and Place
Volume51
DOIs
StatePublished - May 1 2018

Fingerprint

Firearms
violence
Violence
learning
community
educational attainment
cause of death
Health
Marital Status
Poverty
Machine Learning
urban community
machine learning
health
marital status
Research
segregation
surveillance
Cause of Death
social isolation

ASJC Scopus subject areas

  • Health(social science)
  • Geography, Planning and Development
  • Public Health, Environmental and Occupational Health

Cite this

Predictors of firearm violence in urban communities : A machine-learning approach. / Goin, Dana E.; Rudolph, Kara; Ahern, Jennifer.

In: Health and Place, Vol. 51, 01.05.2018, p. 61-67.

Research output: Contribution to journalArticle

@article{d5a58774460f48889a65ae424eaba27a,
title = "Predictors of firearm violence in urban communities: A machine-learning approach",
abstract = "Interpersonal firearm violence is a leading cause of death and injuries in the United States. Identifying community characteristics associated with firearm violence is important to improve confounder selection and control in health research, to better understand community-level factors that are associated with firearm violence, and to enhance community surveillance and control of firearm violence. The objective of this research was to use machine learning to identify an optimal set of predictors for urban interpersonal firearm violence rates using a broad set of community characteristics. The final list of 18 predictive covariates explain 77.8{\%} of the variance in firearm violence rates, and are publicly available, facilitating their inclusion in analyses relating violence and health. This list includes the black isolation and segregation indices, rates of educational attainment, marital status, indicators of wealth and poverty, longitude, latitude, and temperature.",
author = "Goin, {Dana E.} and Kara Rudolph and Jennifer Ahern",
year = "2018",
month = "5",
day = "1",
doi = "10.1016/j.healthplace.2018.02.013",
language = "English (US)",
volume = "51",
pages = "61--67",
journal = "Health and Place",
issn = "1353-8292",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Predictors of firearm violence in urban communities

T2 - A machine-learning approach

AU - Goin, Dana E.

AU - Rudolph, Kara

AU - Ahern, Jennifer

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Interpersonal firearm violence is a leading cause of death and injuries in the United States. Identifying community characteristics associated with firearm violence is important to improve confounder selection and control in health research, to better understand community-level factors that are associated with firearm violence, and to enhance community surveillance and control of firearm violence. The objective of this research was to use machine learning to identify an optimal set of predictors for urban interpersonal firearm violence rates using a broad set of community characteristics. The final list of 18 predictive covariates explain 77.8% of the variance in firearm violence rates, and are publicly available, facilitating their inclusion in analyses relating violence and health. This list includes the black isolation and segregation indices, rates of educational attainment, marital status, indicators of wealth and poverty, longitude, latitude, and temperature.

AB - Interpersonal firearm violence is a leading cause of death and injuries in the United States. Identifying community characteristics associated with firearm violence is important to improve confounder selection and control in health research, to better understand community-level factors that are associated with firearm violence, and to enhance community surveillance and control of firearm violence. The objective of this research was to use machine learning to identify an optimal set of predictors for urban interpersonal firearm violence rates using a broad set of community characteristics. The final list of 18 predictive covariates explain 77.8% of the variance in firearm violence rates, and are publicly available, facilitating their inclusion in analyses relating violence and health. This list includes the black isolation and segregation indices, rates of educational attainment, marital status, indicators of wealth and poverty, longitude, latitude, and temperature.

UR - http://www.scopus.com/inward/record.url?scp=85043512726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043512726&partnerID=8YFLogxK

U2 - 10.1016/j.healthplace.2018.02.013

DO - 10.1016/j.healthplace.2018.02.013

M3 - Article

C2 - 29549755

AN - SCOPUS:85043512726

VL - 51

SP - 61

EP - 67

JO - Health and Place

JF - Health and Place

SN - 1353-8292

ER -