This paper models the stochastic behavior of large-scale terrorist events using extreme value methods. We utilize a unique dataset composed of roughly 24,000 observations. These data provide a rich description of domestic and international terrorism between 1968 and 2005. Currently a credible...

When data include extremes, finite expectations may not exist and rational policymaking fails. We apply methods from Extreme Value Theory to data on mortality rates from respiratory contagions for the US and the world over the 30 years immediately preceding COVID-19. This allows us to ask: Did...