Do Outbreaks of War Follow a Poisson-Process?
In: The journal of conflict resolution: journal of the Peace Science Society (International), Band 28, Heft 1, S. 51-61
ISSN: 1552-8766
Richardson's finding that the distribution of war outbreaks in time conforms to the Poisson distribution has been repeated over and over again. In this article, we argue that the close correspondence between the two distributions does not imply that the mechanism generating the data is the Poisson process. Because the time sequence is broken down in Richardson's analysis, his finding does not imply that war outbreaks follow a distinct pattern in time. The Parzen test on arrival times revealed that war outbreaks are not generated by a Poisson random process.