Predictive models of world conflict: accounting for regional and conflict-state differences

Nicholas J Shallcross and Darryl K Ahner

The Journal of Defense Modeling and Simulation, 2020, vol. 17, issue 3, 243-267

Abstract: Developing nation-conflict forecasting models is of vital importance to international resource allocation strategies that affect regional and worldwide security and stability. A nation in conflict may evolve very differently to one that is not. Using a unique set of open-source data, a suite of region-specific models are developed that predict nation-state transitions into and out of violent conflict. Conflict transition predictor variables differ not only between the regions, but also within each region dependent on if a nation is identified as in conflict or not. Accurate modeling of complex regional environments is achieved with parsimonious and interpretable models. While we ensure the causal variables of the previous study are considered for inclusion in the models developed, this paper focuses on the ability to accurately predict conflict over individual independent variable analysis.

Keywords: Violent conflict; conflict transitions; conflict management; conflict prediction; conditional logistic regression; foreign policy decision making (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://journals.sagepub.com/doi/10.1177/1548512919847532 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:joudef:v:17:y:2020:i:3:p:243-267

DOI: 10.1177/1548512919847532

Access Statistics for this article

More articles in The Journal of Defense Modeling and Simulation
Bibliographic data for series maintained by SAGE Publications ().