Scott J. Cook | Searcharxiv

arXiv2024

Addressing Duplicated Data in Spatial Point Patterns

Spatial point process models are widely applied to point pattern data from various applications in the social and environmental sciences. However, a serious hurdle in fitting point process models is the presence of duplicated points, wherein multiple observations share identical spatial coordinates. This often occurs because of decisions made in the geo-coding process, such as assigning representative locations (e.g., aggregate-level centroids) to observations when data producers lack exact location information. Because spatial point process models like the Log-Gaussian Cox Process (LGCP) assume unique locations, researchers often employ ad hoc solutions (e.g., removing duplicates or jittering) to address duplicated data before analysis. As an alternative, this study proposes a Modified Minimum Contrast (MMC) method that adapts the inference procedure to account for the effect of duplicates in estimation, without needing to alter the data. The proposed MMC method is applied to LGCP models, focusing on the inference of second-order intensity parameters, which govern the clustering structure of point patterns. Under a variety of simulated conditions, our results demonstrate the advantages of the proposed MMC method compared to existing ad hoc solutions. We then apply the MMC methods to a real-data application of conflict events in Afghanistan (2008-2009).

stat.ME↗

arXiv2021

The promise and perils of point process models of political events

Event data are increasingly common in applied political science research. While these data are inherently locational, political scientists predominately analyze aggregate summaries of these events as areal data. In so doing, they lose much of the information inherent to these point pattern data, and much of the flexibility that comes analyzing events using point process models. Recognizing these advantages, applied statisticians have increasingly utilized point process models in the analysis of political events. Yet, this work often neglects inherent limitations of political event data (e.g, geolocation accuracy), which can complicate the direct application of point process models. In this paper, we attempt to bridge this divide: introducing the benefits of point process modeling for political science research, and highlighting the unique challenges political science data pose for these approaches. To ground our discussion, we focus the Global Terrorism Database, using a univariate and bivariate log-Gaussian Cox process model (LGCP) to analyze terror attacks in Nigeria during 2014.

stat.AP↗