Related Experiment Video
Updated: Jan 31, 2026

Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
[Racial and regional inequalities in homicides in Brazil: a geostatistical and propensity score analysis]
Rildo Pinto da Silva1, Antonio Pazin-Filho1
1Faculdade de Medicina de Ribeirão Preto, Universidade de São Paulo. Av. Bandeirantes 3900, Monte Alegre. Ribeirão Preto SP Brasil. rildo.silva@alumni.usp.br.
None:
Studies have demonstrated racial selectivity in homicides in Brazil. This study analyzes racial and regional inequalities in homicides using geostatistical techniques and propensity score methods. Clusters of municipalities with high (hot spots) and low (cold spots) homicide rates were identified and, with demographic variables, were used to calculate propensity scores. After matching, Black individuals had a 49% higher likelihood of dying by homicide compared with White individuals. Homicides occurred predominantly among young, single men with low educational attainment. Geostatistical analysis showed that municipalities in hot spot clusters had homicide rates five times higher than in cold spot clusters, with the Northeast region being the most affected. Skin color remained an independent factor associated with homicide, even after adjusting for demographic and spatial variables, underscoring the racial selectivity of homicide in Brazil. This study proposes an integrated approach combining geospatial analysis and propensity score methods to assess social and spatial inequalities of homicides in the country, providing for more equitable allocation of public policy resources to reduce homicides.
Related Concept Videos
Inequalities
Absolute Value Inequalities
Graphical Representation of Inequalities
Solving Inequalities Graphically
Application of Nonlinear Inequalities
Introduction to Nonlinear Inequalities

