Resumo:
A multidisciplinary study conducted in Minas Gerais investigated the temporal dynamics
of street robberies, analyzing both pre-pandemic and pandemic periods. Utilizing data
from the Military Police, time series data were examined at various scales, including
hourly, daily, 10-day intervals, and monthly, employing advanced statistical methods such
as spectral frequency analysis, autocorrelations, and decomposition techniques. The results
were surprising, revealing an average decrease of 64% in robberies during the pandemic
and identifying a stationary pattern in pandemic occurrences, indicating increased
randomness in the events. Contrary to expectations, no seasonality was observed in robberies
concerning weekdays, the beginning or end of the month, or months of the year.
These findings offer valuable insights into understanding the temporal patterns of crimes
and contribute to the development of more effective public safety policies. Additionally,
the study underscored the usefulness of the geocoder (Geo) in robbery analysis, enabling
the conversion of addresses into geographic coordinates, facilitating the visualization of
the spatial distribution of crimes. The integration of this data with additional geographic
information and the creation of interactive maps using the Leaflet library and the SF
package in the R environment were highlighted as crucial tools for identifying high-crime
areas, regions with reduced police presence, and planning effective public safety strategies,
emphasizing the importance of geospatial data analysis in decision-making in this field.