Escaping the pushpin paradigm in geographic information science: (re)presenting national crime data

Singleton, Alex; Brunsdon, Chris

doi:10.1111/area.12116

Cited by 9 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Focusing on address level or exact repeat analysis though such error will become more problematic (Block and Block, 1995;Eck, Clarke, & Guerette, 2007). Also given that much crime data is disseminated at larger aggregations to preserve privacy (Field, 2011;Singleton & Brunsdon, 2014;Thompson et al, 2015), it suggests this aggregation may be reasonable, given that lower address level dissemination is likely to contain some error.…”

Section: Discussionmentioning

confidence: 99%

“…With modern geographic information systems it is simple to plot crimes on a map to see what appears to be the exact locations of crime incidents and to perform advanced statistical analysis based on those locations. However, it is well known that there are reliability issues with crime data (Tompson et al, 2015;Ratcliffe, 2004;Carr & Doleac, 2016), and the crime maps may portray an image of crime as more exact than what police recorded data can actually capture (Field, 2011;Singleton & Brunsdon, 2014). Crimes can take place anywhere humans can travel to, but are typically recorded to an address or an intersection (Levine & Kim, 1998;Wheeler, Worden, & McLean, 2016), and thus only represent an approximation to where the crime actually took place.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Testing the Spatial Accuracy of Address-Based Geocoding for Gunshot Locations

Wheeler

Gerell

Yoo

2020

The Professional Geographer

View full text Add to dashboard Cite

We assess the positional accuracy of address based geocoding of shooting incidents relative to the location recorded via acoustic gunshot detection technology. This provides a test of the accuracy of typical address based geocoding methods used in crime analysis, as well as provides evidence for how much accuracy one gains when using sensors. Examining over 1,000 shooting incidents in Wilmington, North Carolina, we find that the majority of address-based incidents are quite accurate, on average within 60 feet of the actual location (using a street centerline geocoder), or within 90 feet (using Google rooftop geocoding). However, based on the incident narrative we identify a subset of transcription errors in over 10% of the cases that increases the distance between the true shooting location and that geocoded using address data. This suggests mechanisms to prevent human errors may be more frugal than those relying on sensors in geocoding shooting incidents.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Testing the Spatial Accuracy of Address-Based Geocoding for Gunshot Locations

Wheeler

Gerell

Yoo

2020

The Professional Geographer

View full text Add to dashboard Cite

show abstract

“…Grid cells are used as geocoding in the provided public data, making it difficult to use other geographies, such as street segments (Vandeviver & Steenbeek, ; Weisburd et al, ) or census geographies like blocks or block groups (Bernasco & Block, ; MacDonald et al, ). Crimes are provided at the middle of street segments (Singleton & Brunsdon, ), which provides a degree of privacy but prevents aggregating crimes to census geographies, whose borders are often defined by streets. Pedestrian stops are geocoded to the address level, but many stops (over 50% in this sample) are recorded at intersections (Wooditch & Weisburd, ).…”

Section: Data Descriptionmentioning

confidence: 99%

Testing for similarity in area‐based spatial patterns: Alternative methods to Andresen's spatial point pattern test

Wheeler

Steenbeek

Andresen

2018

Transactions in GIS

View full text Add to dashboard Cite

Andresen's spatial point pattern test (SPPT) compares two spatial point patterns on defined areal units; it identifies areas where the spatial point patterns diverge and aggregates these local (dis)similarities to one global measure. We discuss the limitations of the SPPT and provide two alternative methods to calculate differences in the point patterns. In the first approach we use differences in proportions tests corrected for multiple comparisons. We show how the size of differences matters, as with large point patterns many areas will be identified by SPPT as statistically different, even if those differences are substantively trivial. The second approach uses multinomial logistic regression, which can be extended to identify differences in proportions over continuous time. We demonstrate these methods by identifying areas where pedestrian stops by the New York City Police Department are different from violent crimes for 2006-2016.

show abstract

“…Grid cells are used as the geocoding in the provided public data make it difficult to use other geographies, such as street segments (Weisburd et al, 2014;, or census geographies like blocks or block groups (Bernasco & Block, 2010;MacDonald et al, 2016). Crimes are provided at the middle of street segments (Singleton & Brunsdon, 2014), which provides a degree of privacy, but prevents aggregating crimes to census geographies, whose borders are defined by streets. Pedestrian stops are geocoded to the address level, but many stops (over 50% in this sample) are recorded at intersections .…”

Section: Data Descriptionmentioning

confidence: 99%