ABSTRACT
This study demonstrates how temporal summary statistics can be a guiding tool for big data analyses to unravel temporal patterns of crime and police presence. Simple indicator statistics were used to identify temporal clusters of crimes and police presence, and to investigate potential links between the two. The methodology was applied on an anonymized police database, including reported crime events and police presence data, from a medium-sized European police department. The results illustrated that certain crime types occurred more during the day (e.g., burglaries), while others were more prevalent at night (e.g., drug crimes, motorbike and car theft). Police presence showed dispersed temporal patterns and little temporal focus on any type of crime. The research shows that temporal summary statistics can be used to support an explorative analysis of big datasets and guide subsequent spatiotemporal analyses of crime and police data. The summary statistics offer an accessible approach to analysing extensive datasets of policing activity and improving evidence-based policing strategies.