Association Between Crime, Places, and Neighborhood Characteristics

From REU@MU
Revision as of 17:38, 15 June 2020 by Rbravo (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Student: Ross Bravo
Mentor: Dr. Aleksandra Snowden

Project Description

Crime levels across the U.S. have been declining. Despite this crime has been consistently high in Milwaukee, Wisconsin. Milwaukee’s violent crime rate is over four times higher than the national crime rate or the Wisconsin crime rate. It can be observed that the crime is spatially clustered in certain parts of the city. Prior studies have examined neighborhood characteristics that are associated with crime. However, we don't know as much about the role of place- and neighborhood- characteristics that are associated with crime occurring in close proximity to alcohol selling establishments. The goal of this study is to utilize socio-economic, alcohol license, and crime data from Milwaukee, Wisconsin, aggregated to U.S. census block groups and estimate spatially lagged regression models to identify key factors that may be used to predict crime occurring in close proximity to alcohol selling establishments. These findings have the potential to inform theoretical explanations of the alcohol-violence relationship and may be beneficial when considering and designing custom tailored local alcohol policy to reduce alcohol-related crime.

Project Tasks

  • Reading literature on neighborhoods, places, and crime.
  • Identifying how to quantify theoretical concepts (i.e., neighborhoods, social disorganization, crime).
  • Develop a testable hypotheses on the association between crime, places, and neighborhood characteristics.
  • Survey and collect appropriate publicly available crime data.
  • Download, pre-process, and manage geospatial data; prepare datasets for analyses.
  • Estimate exploratory spatial data models.
  • Estimate spatial regression models.

General Outline

Week Description
Week 1
  • Participate in REU data science boot-camp and orientation
Weeks 2-4
  • Read theoretical and empirical literature provided by mentor and any other relevant prerequisite literature.
  • Attempt to quantify neighborhoods, social disorder, and crime, with each new reading.
Weeks 5-6
  • Form a testable hypothesis.
  • Begin to survey data.
  • Appropriately select data and begin to clean/processes it.
  • Begin to test hypothesis.
Week 7
  • Create exploratory spatial data models and spatial regression models.
  • Begin the final report research paper
Week 8-9
  • Finish research paper.
  • Begin peer review and editing of paper.
  • Complete poster for presentation.
Week 10
  • Have paper finalized and then submit.
  • Prepare and give an oral presentation on work.
  • Present poster at poster session