Authors:Dawn Williams (University College London) (Speaker) James Haworth (University College London)Marta Blangiardo (Imperial College London)Tao Cheng (Imperial College London)
Improving understanding of public confidence at the local level willbetter enable the police to conduct proactive confidence interventions to meet the concerns of local communities. Neighbourhood level approaches to modelling public confidence in the police are hampered by the small number problem and the resulting instability in the estimates and uncertainty in the results. Furthermore, they do not consider that public confidence varies across geographic space as well as in time. Bayesian hierarchical methods provide a flexible framework for overcoming these issues. This study illustrates a spatiotemporal Bayesian mixture modelling approach for investigating instability in public confidence at the neighbourhood level which overcomes the limitations of the small number problem. Our spatiotemporal Bayesian hierarchical model, comprised of a spatial and temporal random effects which estimate stable or “predictable” temporal patterns and a dynamic spatiotemporal interaction component allows the full spatiotemporal profile of the phenomenon to be investigated. This approach produced more accurate estimates than direct methods and allows neighbourhoods to be classified and compared.
Keywords: Bayesian mixture modelling spatiotemporal policing neighbourhood level.