Testing for similarity in area-based spatial patterns: how the pattern of pedestrian stops by the NYPD differs from crime (2006-2016)

Abstract

Andresen’s spatial point pattern test (SPPT) can be used to compare two spatial point patterns on defined areal units: it identifies in which particular areas the spatial point patterns diverge and aggregates these local (dis)similarities to one global measure. It has been widely applied to geographic analyses of crime and police behavior. We discuss the limitations of the SPPT and we provide two alternative methods. In one approach we use differences in proportions tests, which can be corrected for multiple comparisons. We then show how to emphasize the size of differences in subsequent maps, as with large point patterns many areas will be identified as different, even if those differences are substantively trivial. The second approach uses multinomial logistic regression, which can then be extended to identify differences in proportions over continuous time. We demonstrate these methods on identifying areas where pedestrian stops by the New York City Police Department are different from violent crimes from 2006 through 2016.

Wouter Steenbeek

Senior Researcher

My research interests include spatio-temporal patterns of crime, offender decision-making, neighborhoods, machine learning, and R.