Análise espacial dos homicídios nos municípios do Estado do Paraná

Abstract

The central objective of this research was to analyze the spatial distribution of homicides in the state of Paraná, over the years 2001 and 2005 and the relationship between this phenomenon and socioeconomic, demographic and urban infrastructure variables as well. The method of Exploratory Spatial Data Analysis (ESDA) was used to measure the degree of spatial autocorrelation among the studied variables, based on the characteristics of the 399 municipalities in the State of Paraná, presently. Initially, the ESDA was used to check the existence of spatial autocorrelation among the state municipalities considering the homicide rates. The results demonstrated the existence of spatial autocorrelation of homicide rates in the municipalities of Paraná State. When considering the mapping of clusters, there was the indicative of four clusters of High High type- (HH) and four large clusters of low-low type (LL). The highest homicide rates were found in clusters of municipalities located in the Metropolitan Mesoregion of Curitiba, in the North Central Mesoregion, West Mesoregion, and in a number of municipalities from Center South, Center West, West and Southwest Mesoregions. The clusters of type LL were in the Northwest and in the Central North Mesoregion, and Pioneiro North and Southwest Mesoregion. The common manifestations of variables in the four clusters of HH type were: the high average of residents per home (ARH), the high number of head of family without income, low number of kindergartens, low number of cultural facilities, low number of people over 60 years and the low incidence of infant mortality. The other tested variables autocorrelated in the cities with the rates of murder, but according to their particular regions. The exception was the variables: water supply and sewerage, per capita Gross Domestic Product (GDP) and head of family over 15 years literate, not significant, at a 5% significance.