Application of negative binomial and linear regression analysis in assessing spatial and temporal trends of alcohol outlet density and aggravated assault in the City of Pittsburgh between 2000 and 2012

Christopher, Phyon (2015) Application of negative binomial and linear regression analysis in assessing spatial and temporal trends of alcohol outlet density and aggravated assault in the City of Pittsburgh between 2000 and 2012. Master Essay, University of Pittsburgh.

	Microsoft Word Submitted Version Available under License : See the attached license file. Download (120kB)
	Plain Text (licence) Available under License : See the attached license file. Download (1kB)

Abstract

Objective: This study examines the public health significance of recent legislature change which allows for the acquisition of a wider variety of alcohol retail licenses. The temporal trend in alcohol retail density and its effect on aggravated assault in the city of Pittsburgh is assessed by comparing data from 2000 and 2012. Previous studies have concluded that there is an association between alcohol outlet density (AOD) and violence, but many of these studies are inconsistent with some reporting an association between AOD and violence and others reporting no increase in risk of violence. Methods: Data for this study was geocoded to determine alcohol outlet density within Pittsburgh from InfoUSA and Dun&Bradstreet; population and demographic data was geocoded from the US Census Bureau; neighborhood level rates of violence were calculated from data provided by the Pittsburgh police department; and data pertaining to 11 neighborhood characteristics were extracted from Summary File 1 and Summary File 3 of the 2000 and 2010 US Census. The association between AOD and violence was assessed using negative binomial regression; the temporal relationship was assessed using linear regression modeling. As a proxy for commercial activity, “restaurant outlet density” (restaurants) was added to the negative binomial models to check for robustness. Results: The model building process produced 16 results: 8 for data where the rates were divided per capita and 8 where the rates were divided per square miles. In 2000 all models produced the same result. Initially they were significant and became non-significant once “restaurants” was added to the model. In 2012 almost all models remained significant after adding restaurants except for the off-premise alcohol retail density per square miles rates in 2012. In 2012 some of the models also changed from positive to negative association after adding restaurants to the models. The linear models all showed that there was no association between the change in AOD and the change in aggravated assault. Conclusions: The results of this study suggest a weak or no association between AOD and aggravated assault. When models are created without “restaurants” added, all models produce relative risk values approximately equal to 1 which shows that AOD does not impact the risk of violence. After restaurants are added to the model almost all predictors of interest become non-significant. These two results confirm that the association either isn’t present or is not as strong as previous literature reported.

---

Share

Citation/Export:	Select format... Citation - Text Citation - HTML Endnote BibTex Dublin Core OpenURL MARC (ISO 2709) METS MODS EP3 XML Reference Manager Refer
Social Networking:	Share |

---

Details

Item Type:	Other Thesis, Dissertation, or Long Paper (Master Essay)
Status:	Unpublished
Creators/Authors:	Creators Email Pitt Username ORCID Christopher, Phyon
Contributors:	Contribution Contributors Name Email Pitt Username ORCID Committee Chair Fabio, Anthony afabio@pitt.edu AFABIO UNSPECIFIED Committee Member Gary-Webb, Tiffany L. tgary@pitt.edu TGARY UNSPECIFIED
Date:	August 2015
Date Type:	Submission
Defense Date:	24 August 2015
Submission Date:	20 July 2015
Access Restriction:	No restriction; Release the ETD for access worldwide immediately.
Publisher:	University of Pittsburgh
Institution:	University of Pittsburgh
Schools and Programs:	School of Public Health > Epidemiology
Degree:	MPH - Master of Public Health
Thesis Type:	Master Essay
Refereed:	Yes
Uncontrolled Keywords:	Alcohol, Outlet, Density, Aggravated, Assault
Date Deposited:	01 Mar 2016 18:52
Last Modified:	01 Aug 2023 10:55
URI:	http://d-scholarship.pitt.edu/id/eprint/25683

---

Metrics

Monthly Views for the past 3 years

Plum Analytics

---

Actions (login required)

View Item