Spatio-temporal mixed membership models for criminal activity
Publication Date
2021-10Journal Title
Journal of the Royal Statistical Society. Series A: Statistics in Society
ISSN
0964-1998
Publisher
Wiley
Volume
184
Issue
4
Pages
1220-1244
Language
en
Type
Article
This Version
AO
VoR
Metadata
Show full item recordCitation
Virtanen, S., & Girolami, M. (2021). Spatio-temporal mixed membership models for criminal activity. Journal of the Royal Statistical Society. Series A: Statistics in Society, 184 (4), 1220-1244. https://doi.org/10.1111/rssa.12642
Abstract
Abstract: We suggest a probabilistic approach to study crime data in London and highlight the benefits of defining a statistical joint crime distribution model which provides insights into urban criminal activity. This is achieved by developing a hierarchical mixture model for observations, crime occurrences over a geographical study area, that are grouped according to multiple time stamps and crime categories. The mixture components correspond to spatial crime distributions over the study area and the goal is to infer, based on the observations, how and to what degree the latent distributions are shared across the groups.
Keywords
ORIGINAL ARTICLE, ORIGINAL ARTICLES, Bayesian statistics, high‐dimensional data, latent factor models, multi‐view modelling, spatial and temporal methods
Sponsorship
EPSRC (EP/P020720/2)
EPSRC (EP/R018413/2)
Engineering and Physical Sciences Research Council (EP/R034710/1)
Royal Academy of Engineering (RAEng) (RCSRF\1718\6\34)
Identifiers
rssa12642
External DOI: https://doi.org/10.1111/rssa.12642
This record's URL: https://www.repository.cam.ac.uk/handle/1810/330119
Rights
Licence:
http://creativecommons.org/licenses/by/4.0/
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.