A Bayesian Aoristic Logistic Regression to Model Spatio-Temporal Crime Risk Under the Presence of Interval-Censored Event Times

Crime data analysis has gained significant interest due to its peculiarities. One key characteristic of property crimes is the uncertainty surrounding their exact temporal location, often limited to a time window.

This study introduces a spatio-temporal logistic regression model that addresses the challenges posed by temporal uncertainty in crime data analysis. Inspired by the aoristic method, our Bayesian approach allows for the inclusion of temporal uncertainty in the model.

To demonstrate the effectiveness of our proposed model, we apply it to both simulated datasets and a dataset of residential burglaries recorded in Valencia, Spain. We compare our proposal with a complete cases model, which excludes temporally-uncertain events, and also with alternative models that rely on imputation procedures. Our model exhibits superior performance in terms of recovering the true underlying crime risk.

The proposed modeling framework effectively handles interval-censored temporal observations while incorporating covariate and space–time effects. This flexible model can be implemented to analyze crime data with uncertainty in temporal locations, providing valuable insights for crime prevention and law enforcement strategies.