IMAGe Seminar- Estimating the Historical and Future Probabilities of Large Terrorist Events

01/15/2016 - 12:00pm to 1:00pm
Mesa Lab- Main Seminar Room

Aaron Clauset, University of Colorado Boulder

Friday, January 15, 2016
12:00 p.m.-1:00 p.m.
Mesa Lab, Main Seminar Room

Quantities with right-skewed distributions are ubiquitous in complex systems, including political conflicts, natural disasters, economics, and social networks, and these systems sometimes produce extremely large events. For instance, the 9/11 terrorist events produced nearly 3000 fatalities, nearly six times more than the next largest event in the past 40 years. But, was this enormous loss of life statistically unlikely given modern terrorism’s historical record? Accurately estimating the probability of such an event is complicated by the large fluctuations in the empirical distribution’s upper tail.

In this talk, I present a generic statistical algorithm for making such judgements, which combines semi-parametric models of tail behavior and a non-parametric bootstrap. Applied to a global database of terrorist events, the method estimates the worldwide historical probability of observing at least one 9/11-sized or larger event since 1968 to be 11–35%. These results remain even when we condition on global variations in economic development, domestic versus international events, the type of weapon used and a truncated history that stops at 1998. I will also show results for using this technique to make a data-driven statistical forecast of at least one similar event over the next decade. To close, I will briefly discuss the applicability of this technique to other complex systems with heavy-tailed distributions of event sizes.

Joint work with Ryan Woodard (ETH Zurich).