Analysis of intentional lethal violent crimes: A sliding windows approach

This paper analyzes the fluctuations in time series of intentional lethal violent crime rates in Salvador, Bahia, Brazil from 2012 to 2018. The modeling proposed was performed with two main strategies: first, the descriptive of the series under study was defined using the sliding window approach, as determined by autocorrelation from Detrended Fluctuation Analysis (DFA), also with sliding window. Results of this research indicate that the series of DFA exponents, depending on the window (365 or 1000 days) and period, have oscillated between persistent, antipersistent and out of memory. Descriptive analysis identified reduction in the average crime rates from 2013 and a behavioral pattern among other moments. These findings will serve as another methodological proposal for monitoring, control and management of criminal indicators and research on them. (C) 2020 Published by Elsevier B.V.

Automated summary

This paper analyzes the fluctuations in intentional lethal violent crime rates in Salvador, Bahia, Brazil from 2012 to 2018. The study found that the series of DFA exponents fluctuated between persistent, antipersistent, and out of memory depending on the window and period used. Descriptive analysis identified a decrease in average crime rates since 2013 and revealed different behavioral patterns at various moments.