Para receber por e-mail novas publicações de Seminário de Palestra Especial, Clique Aqui!

Seminários do IMPA

Palestra Especial

Nonparametric spatiotemporal analysis of violent crime. A case study in the Rio de Janeiro metropolitan area
Wenceslao González–Manteiga

Universidade de Santiago de Compostela
Quarta-feira, 15 de maio de 2019, 13:30
Auditorio Ricardo Mañé

This presentation concerns the spatiotemporal point pattern of gunfire reports collected by  the app “Fogo Cruzado” during the year of 2017, which comprises the location and time of occurrence of each gun shooting as well as some additional information.

Kernel hotspot maps and self-exciting point process models have been widely used to predict crime incidence in other areas. Prior to applying any of these approaches we should test if the gunfire patterns fulfill their assumptions. For this purpose, we have applied nonparametric first and second-order point process inference. The kernel intensity estimator describes the spatial distribution of gunfire and allows us to identify chronic hotspots.

The results suggest that we could consider a self-exciting point process with nonseparable background component as a starting point in the development of a suitable approach to forecast gunfire hotspots in Rio de Janeiro.

Joint work with  Isabel Fuentes-Santos (Marine Research Institute, Vigo, Spain) and Jorge P. Zubelli (IMPA, Brazil).