Statistics vs machine learning: an application on time-to-event data in terrorist kidnapping events
DOI:
https://doi.org/10.71014/sieds.v80i2.429Abstract
Hostage-taking durations in terrorist attacks using the Global Terrorism Database have been considered in this paper using data from 1970 to 2021. Employing conditional inference trees and Cox proportional hazards models, we managed to determine factors influencing hostage release time. Attack type and ransom demands significantly prolong incident duration, with effects varying over time. Regional variations have also been detected, with Middle East & North Africa and Southeast Asia showing longer median durations. The complementary insights from machine learning providing a clustering of individuals based on survival time and statistical methodologies which provide a clustering of the effects of the covariates on the instantaneous risk of surviving yield a robust framework for understanding complex events such as kidnapping.
References
BRANDT P.T., SANDLER T. 2009. Hostage taking: Understanding terrorism event dynamics, Journal of Policy Modeling, Vol. 31, No. 5, pp. 758–778.
COX D.R. 1972. Regression models and life-tables (with discussion), Journal of the Royal Statistical Society. Series B (Methodological), Vol. 34, No. 2, pp. 187–220.
DELOUGHERY K., KING R.D., ASAL V. 2012. Close cousins or distant relatives? The relationship between terrorism and hate crime, Crime & Delinquency, Vol. 58, No. 5, pp. 663–688.
DUGAN L., LAFREE G., PIQUERO A.R. 2005. Testing a rational choice model of airline hijackings, Criminology, Vol. 43, No. 4, pp. 1031–1065.
ENDERS W., SANDLER T. 2012. The Political Economy of Terrorism. Cambridge: Cambridge University Press.
GAIBULLOEV K., SANDLER T. 2009. Hostage taking: Determinants of terrorist logistical and negotiation success, Journal of Conflict Resolution, Vol. 46, No. 6, pp. 882–901.
HOTHORN T., HORNIK K., ZEILEIS A. 2006. Unbiased recursive partitioning: A conditional inference framework, Journal of Computational and Graphical Statistics, Vol. 15, No. 3, pp. 651–674.
HOTHORN T., ZEILEIS A. 2015. partykit: A Modular Toolkit for Recursive Partytioning in R, Journal of Machine Learning Research, Vol. 16, pp. 3905–3909.
KAPLAN E.L., MEIER P. 1958. Nonparametric estimation from incomplete observations, JASA, Vol. 53, No. 282, pp. 457–481.
KIM W., SANDLER T. 2021. Non-UN Peacekeeping Effectiveness: Further Analysis, Defense and Peace Economics, Vol. 33, No. 5, pp. 511–533.
LAFREE G., DUGAN L. 2007. Introducing the Global Terrorism Database, Terrorism and Political Violence, Vol. 19, No. 2, pp. 181–204.
PHILLIPS B.J. 2014. Terrorist group cooperation and longevity, International Studies Quarterly, Vol. 58, No. 2, pp. 336–347.
PHILLIPS P.J. 2011. The Diseconomies of Terrorism, World Economics, Vol. 12, No. 4, pp. 171–192.
PIAZZA J.A. 2017. Repression and terrorism: A cross-national empirical analysis of types of repression and domestic terrorism, Terrorism and Political Violence, Vol. 29, No. 1, pp. 102–118.
START - National Consortium for the Study of Terrorism and Responses to Terrorism. 2022. Global Terrorism Database (GTD). Retrieved from http://www.start.umd.edu/gtd
WHITE G., MAZEROLLE L., PORTER M., CHALK P. 2014. Modelling the effectiveness of counter-terrorism interventions, Trends & Issues in Crime and Criminal Justice, No. 475. Canberra: Australian Institute of Criminology.
WILSON M.A. 2000. Toward a model of terrorist behavior in hostage-taking incidents, Journal of Conflict Resolution, Vol. 44, No. 4, pp. 403-424.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Luciano Nieddu, Cecilia Vitiello
This work is licensed under a Creative Commons Attribution 4.0 International License.
