Modeling terror attacks: A cross-national, out-of-sample study

Ryan Bakker, Daniel W. Hill, Will H. Moore

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Purpose - The purpose of this study is to assess the ability of a theoretically motivated statistical model to accurately forecast annual, national counts of terror attacks out-of-sample. Methodology/approach - Bayesian multi-level models, classification analysis, marginal calibration plots Findings - We find that the model forecasts reasonably well, but conclude that its overall performance suggests that it is not ready for use in policy planning. This is likely due to the coarse temporal and spatial aggregation of the data. Research limitations/implications - The implications of this study are that social scientists should devote more effort into evaluating the predictive power of their statistical models, and that annual, national data on violent conflict are probably too coarse to provide useful information for policy planning. Originality/value of paper- The primary value of our modeling effort is to provide a baseline against which to evaluate the performance of more region- And country-specific models to be developed in the future.

Original languageEnglish (US)
Title of host publicationContributions to Conflict Management, Peace Economics and Development
PublisherElsevier
Pages51-68
Number of pages18
Volume22
ISBN (Print)9781783508273
DOIs
StatePublished - 2014
Externally publishedYes

Publication series

NameContributions to Conflict Management, Peace Economics and Development
Volume22
ISSN (Print)15728323

Fingerprint

terrorism
modeling
planning
social scientist
aggregation
performance
Attack
Terror
Statistical model
Modeling
Cross-national
Policy planning
calibration
methodology
ability
Values
Predictive power
Calibration
Bayesian approach
Marginal analysis

Keywords

  • Dissent
  • Events
  • Forecasting
  • Repression
  • Terror
  • Violence

ASJC Scopus subject areas

  • Political Science and International Relations
  • Development
  • Sociology and Political Science
  • Business and International Management
  • Strategy and Management

Cite this

Bakker, R., Hill, D. W., & Moore, W. H. (2014). Modeling terror attacks: A cross-national, out-of-sample study. In Contributions to Conflict Management, Peace Economics and Development (Vol. 22, pp. 51-68). (Contributions to Conflict Management, Peace Economics and Development; Vol. 22). Elsevier. https://doi.org/10.1108/S1572-8323(2014)0000022008

Modeling terror attacks : A cross-national, out-of-sample study. / Bakker, Ryan; Hill, Daniel W.; Moore, Will H.

Contributions to Conflict Management, Peace Economics and Development. Vol. 22 Elsevier, 2014. p. 51-68 (Contributions to Conflict Management, Peace Economics and Development; Vol. 22).

Research output: Chapter in Book/Report/Conference proceedingChapter

Bakker, R, Hill, DW & Moore, WH 2014, Modeling terror attacks: A cross-national, out-of-sample study. in Contributions to Conflict Management, Peace Economics and Development. vol. 22, Contributions to Conflict Management, Peace Economics and Development, vol. 22, Elsevier, pp. 51-68. https://doi.org/10.1108/S1572-8323(2014)0000022008
Bakker R, Hill DW, Moore WH. Modeling terror attacks: A cross-national, out-of-sample study. In Contributions to Conflict Management, Peace Economics and Development. Vol. 22. Elsevier. 2014. p. 51-68. (Contributions to Conflict Management, Peace Economics and Development). https://doi.org/10.1108/S1572-8323(2014)0000022008
Bakker, Ryan ; Hill, Daniel W. ; Moore, Will H. / Modeling terror attacks : A cross-national, out-of-sample study. Contributions to Conflict Management, Peace Economics and Development. Vol. 22 Elsevier, 2014. pp. 51-68 (Contributions to Conflict Management, Peace Economics and Development).
@inbook{51b55c611dd246e0ad5b84127eebc52a,
title = "Modeling terror attacks: A cross-national, out-of-sample study",
abstract = "Purpose - The purpose of this study is to assess the ability of a theoretically motivated statistical model to accurately forecast annual, national counts of terror attacks out-of-sample. Methodology/approach - Bayesian multi-level models, classification analysis, marginal calibration plots Findings - We find that the model forecasts reasonably well, but conclude that its overall performance suggests that it is not ready for use in policy planning. This is likely due to the coarse temporal and spatial aggregation of the data. Research limitations/implications - The implications of this study are that social scientists should devote more effort into evaluating the predictive power of their statistical models, and that annual, national data on violent conflict are probably too coarse to provide useful information for policy planning. Originality/value of paper- The primary value of our modeling effort is to provide a baseline against which to evaluate the performance of more region- And country-specific models to be developed in the future.",
keywords = "Dissent, Events, Forecasting, Repression, Terror, Violence",
author = "Ryan Bakker and Hill, {Daniel W.} and Moore, {Will H.}",
year = "2014",
doi = "10.1108/S1572-8323(2014)0000022008",
language = "English (US)",
isbn = "9781783508273",
volume = "22",
series = "Contributions to Conflict Management, Peace Economics and Development",
publisher = "Elsevier",
pages = "51--68",
booktitle = "Contributions to Conflict Management, Peace Economics and Development",

}

TY - CHAP

T1 - Modeling terror attacks

T2 - A cross-national, out-of-sample study

AU - Bakker, Ryan

AU - Hill, Daniel W.

AU - Moore, Will H.

PY - 2014

Y1 - 2014

N2 - Purpose - The purpose of this study is to assess the ability of a theoretically motivated statistical model to accurately forecast annual, national counts of terror attacks out-of-sample. Methodology/approach - Bayesian multi-level models, classification analysis, marginal calibration plots Findings - We find that the model forecasts reasonably well, but conclude that its overall performance suggests that it is not ready for use in policy planning. This is likely due to the coarse temporal and spatial aggregation of the data. Research limitations/implications - The implications of this study are that social scientists should devote more effort into evaluating the predictive power of their statistical models, and that annual, national data on violent conflict are probably too coarse to provide useful information for policy planning. Originality/value of paper- The primary value of our modeling effort is to provide a baseline against which to evaluate the performance of more region- And country-specific models to be developed in the future.

AB - Purpose - The purpose of this study is to assess the ability of a theoretically motivated statistical model to accurately forecast annual, national counts of terror attacks out-of-sample. Methodology/approach - Bayesian multi-level models, classification analysis, marginal calibration plots Findings - We find that the model forecasts reasonably well, but conclude that its overall performance suggests that it is not ready for use in policy planning. This is likely due to the coarse temporal and spatial aggregation of the data. Research limitations/implications - The implications of this study are that social scientists should devote more effort into evaluating the predictive power of their statistical models, and that annual, national data on violent conflict are probably too coarse to provide useful information for policy planning. Originality/value of paper- The primary value of our modeling effort is to provide a baseline against which to evaluate the performance of more region- And country-specific models to be developed in the future.

KW - Dissent

KW - Events

KW - Forecasting

KW - Repression

KW - Terror

KW - Violence

UR - http://www.scopus.com/inward/record.url?scp=84901456440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901456440&partnerID=8YFLogxK

U2 - 10.1108/S1572-8323(2014)0000022008

DO - 10.1108/S1572-8323(2014)0000022008

M3 - Chapter

AN - SCOPUS:84901456440

SN - 9781783508273

VL - 22

T3 - Contributions to Conflict Management, Peace Economics and Development

SP - 51

EP - 68

BT - Contributions to Conflict Management, Peace Economics and Development

PB - Elsevier

ER -