Prediction of Intrastate Conflict Using State Structural Factors and Events Data

Abstract

The primary objective of this article is to advance the development of early warning of intrastate conflict by combining country-level structural and events data in a logistic regression model calibrated and validated using split-sample cases. Intrastate conflict is defined by the occurrence of one or more highly destabilizing events collectively termed a crisis of interest (COI). Two separate two-year periods between 1990 and 2005 were examined in twenty-five globally dispersed countries. COIs occurred in about 6 percent of all the half-monthly periods examined. While model accuracy (total correct predictions of COI and non-COI) usually exceeded 90 percent, the model did not generate sufficiently high and consistent precision (correct number of COI over total predicted) and recall (correct number of COI over total observed) for practical use.

Quantitative Assessment of Political Fragility Indices and Food Prices as Indicators of Food Riots in Countries

“…Among the quantitative research, we find different approaches to measuring political fragility: dynamic (e.g., econometric models), structural (e.g., indices of political fragility) and a combination between these [40]. This growing body of research has evidenced a link between the natural environment and instability [35] and an increase in the occurrence and intensity of intra-state conflict.…”

Sociocultural Behavior Sensemaking: State of the Art in Understanding the Operational Environment

“…Automated methods for extracting event data from news feeds have been developed for various regions and contexts (Schrodt, 2012). In particular, some researchers have suggested the integration of event data with leadership rhetoric as a way to improve forecasts of the onset of intrastate conflicts such as insurgencies (Tikuisis, Carment, & Samy, 2013).…”

Will the real security foresight expert please stand up?

“…Weak signals are small changes that are currently observable but may only trigger bigger changes in the future. These can be incorporated into statistical models, where accounting for certain destabilizing events in conjunction with latent structural risk factors may allow for the early-warning of an impending political crisis [47]. Likewise, unexpected outcomes may result from agent-based simulations as emergent phenomena due to micro-level interactions with initially unclear implications.…”