Reincidencia de la Población Carcelaria a Cargo del Instituto Nacional Penitenciario en Colombia; Caracterización y Modelamiento Estadístico

Abstract

This document presents a comprehensive analysis of the prison population in Colombia, with a particular focus on prison recidivism and the historical count of recidivism per individual. Using data provided by the National Penitentiary Institute of Colombia (INPEC), various social, demographic, and judicial characteristics will be explored to identify recurring profiles. Given the inflation of zeros in the recidivism distribution, different statistical models, including zero-inflated count models and zero-truncated count models, such as Poisson Regression, Negative Binomial Regression, Zero-Inflated Poisson (ZIP), Zero- Inflated Negative Binomial, Zero-Truncated Poisson, and Zero-Truncated Negative Binomial, will be compared and applied. Additionally, a recidivism score will be estimated to identify profiles prone to criminal recidivism. This study aims to shed light on the dynamics of prison recidivism in Colombia and provide insights that can contribute to the formulation of policies and reintegration programs within the country’s penal system, aiming for the best prediction and accurate recidivism counts.