Estimation of Spatiotemporal Poisson Processes with Some Missing Location Data

TL;DR

This paper develops models for spatiotemporal Poisson processes with missing location data, demonstrating their effectiveness on emergency call data where location information is often incomplete.

Contribution

It introduces four models that handle missing location data in spatiotemporal Poisson processes and provides estimation methods for these models.

Findings

Models improve estimation accuracy with missing data

Application to emergency call data shows practical benefits

Code available on GitHub for reproducibility

Abstract

We consider models for spatiotemporal Poisson processes with some missing location data. We discuss four models that make provision for missing location data, and their estimation. The corresponding code is available on GitHub as an extension of LASPATED at https://github.com/vguigues/LASPATED/Missing_Data. We tested our models using the process of emergency call arrivals to an emergency medical service where the emergency reports often omit the location of the emergency. We show the difference made by using models that make provision for missing location data.