Statistical modeling of impunity: inferential and predictive methods for crime data in the state of São Paulo

• Grant number: 24/23688-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: March 01, 2025
• End date: February 28, 2026
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Applied Probability and Statistics
• Principal Investigator: Luis Gustavo Nonato
• Grantee: Ada Maris Pereira Mário
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 22/09091-8 - Criminality, insecurity, and legitimacy: a transdisciplinary approach, AP.ESCIENCE.TEM

Abstract

Crime in Brazil presents growing challenges for public administration. Among these, accessing, understanding, and explaining impunity is essential for improving the system. This scientific initiation project proposes the study and development of inferential and predictive methods for the analysis and modeling of crime data in the state of São Paulo, with an emphasis on impunity. Bayesian models, including ICAR (Intrinsic Conditional Auto-Regressive) and CAR (Conditional Auto-Regressive) models, will be investigated, as well as their properties and performance in comparative studies of statistical methods with predictive approaches for modeling impunity. Additionally, the project will contribute to discussions and inferential studies of the data generated and organized by the thematic project "Criminality, Insecurity, and Legitimacy: A Transdisciplinary Approach" (Process: 22/09091-8), which aims to develop innovative analytical methodologies to investigate complex phenomena associated with impunity, crime, the perception of insecurity, and the legitimacy of justice institutions.