Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


37937.pdf (27.52 MB)

ETD Abstract Container

Abstract Header

Proposing and Assessing Facility Risk Measures for Place Based Studies of Crime

Henderson, Samantha M.
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1613749820830332

Abstract Details

2020, PhD, University of Cincinnati, Education, Criminal Justice, and Human Services: Criminal Justice.
OBJECTIVES. This study addresses a shortcoming in the facility measurement approach used in some studies of crime and place. That is, researchers tend to treat facilities as though they have a homogenous crime risk despite research indicating there is significant variation in crime across facilities. In this study, I propose and examine a series of eight empirically rooted alternative measures of risky facilities. I assess what, if any, impact each has on the outcomes of models of robbery and theft at street blocks in Cincinnati, Ohio, as compared to the more commonly used homogenous risk measure. METHODS. To compare facility risk measures, I use a series of nearly identical negative binomial regressions to model the effects of sixteen facility types on robbery and theft at street blocks. Models vary only in their operationalization of facility risk. I use model comparison statistics (AIC, BIC) to determine if any of the proposed facility risk variables offer an improved model fit over the homogenous facility crime risk approach. For those that result in an improved fit, I assess model coefficients and significance to determine if the conclusions differ meaningfully from those derived from the homogenous facility crime risk approach. RESULTS. Of the eight proposed measures, only the continuous measure created using calls for service within a 500ft buffer area offered an improved model fit, and only for robbery. The conclusions drawn from the proposed measure regression results largely mirrored those of the homogenous facility count regression results. A number of other models that did not have an improved fit were impacted by multicollinearity, possibly due to the presence of co-located facilities with shared addresses. CONCLUSION. A continuous crime risk variable created using calls for service data within an approximately one block buffer area of facilities may act as an acceptable alternative measure of facility robbery risk in future studies of crime and place. However, this measure is limited by its less intuitive coefficient interpretation and the possibility of biased results in study areas with a high number of facilities with shared addresses. Measuring facilities using simple counts remains a viable operationalization according to the results of this study.
Cory Haberman, Ph.D. (Committee Chair)
Martin Andresen, Ph.D. (Committee Member)
John Eck, Ph.D. (Committee Member)
Pamela Wilcox, Ph.D. (Committee Member)
207 p.
Criminology
Environmental Criminology; Geography of crime; Criminology of place; Risky facilities

Recommended Citations

Citations

  • Henderson, S. M. (2020). Proposing and Assessing Facility Risk Measures for Place Based Studies of Crime [Doctoral dissertation, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1613749820830332

    APA Style (7th edition)

  • Henderson, Samantha. Proposing and Assessing Facility Risk Measures for Place Based Studies of Crime. 2020. University of Cincinnati, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1613749820830332.

    MLA Style (8th edition)

  • Henderson, Samantha. "Proposing and Assessing Facility Risk Measures for Place Based Studies of Crime." Doctoral dissertation, University of Cincinnati, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1613749820830332

    Chicago Manual of Style (17th edition)

ucin1613749820830332
159
© 2020, some rights reserved.Creative Commons License Proposing and Assessing Facility Risk Measures for Place Based Studies of Crime by Samantha M. Henderson is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. Based on a work at etd.ohiolink.edu.
This open access ETD is published by University of Cincinnati and OhioLINK.