A time‐series analysis of transnational terrorism: Trends and cycles
- 1 November 1992
- journal article
- research article
- Published by Taylor & Francis in Defence Economics
- Vol. 3 (4) , 305-320
- https://doi.org/10.1080/10430719208404739
Abstract
Spectral analysis is applied to transnational terrorist time series involving all incidents, hostage incidents, bombings, assassinations, and threats and hoaxes during 1970–1989. Cycles characterize all of the series: Cycles of 7.2 quarters periodicity were found for bombings and the total of all incidents; cycles of 18 quarters were found for hostage events, all incidents, and assassinations; and cycles of 3.6 quarters were found for threats and hoaxes. Logistical complexity was positively related to the length of the cycle. Linear trend was associated with hostage events and total events, while nonlinear trend was associated with assassinations, and threats and hoaxes. Bombings showed no trend. Bombings, total incidents, and hostage events displayed stationary series due to the absence of a unit root. Assassinations and threats were nonstationary but not cointegrated. Given the regularity of cycles and the trend components uncovered, there is a clear need to develop a theoretical framework capable of explaining these cycles and trends.Keywords
This publication has 9 references indexed in Scilit:
- Assessing the impact of terrorist‐thwarting policies: An intervention time series approachDefence Economics, 1990
- Time Series Models for Count or Qualitative ObservationsJournal of Business & Economic Statistics, 1989
- The predictability of international terrorism: A time‐series analysisTerrorism, 1988
- Time Series Analysis of a Contagious ProcessJournal of the American Statistical Association, 1987
- Cycles and Substitutions in Terrorist Activities: A Spectral ApproachKyklos, 1987
- Dynamics of TerrorismInternational Studies Quarterly, 1983
- Likelihood Ratio Statistics for Autoregressive Time Series with a Unit RootEconometrica, 1981
- Distribution of the Estimators for Autoregressive Time Series With a Unit RootJournal of the American Statistical Association, 1979
- Analyzing Diffusion and Contagion Effects: The Urban Disorders of the 1960sAmerican Political Science Review, 1978