Rare events

Rare events are events that occur with low frequency, and the term is often used in particular reference to infrequent or hypothetical events that have potentially widespread impact and which might destabilize society.[1] Rare events encompass natural phenomena (major earthquakes, tsunamis, hurricanes, floods, asteroid impacts, solar flares, etc.), anthropogenic hazards (warfare and related forms of violent conflict, acts of terrorism, industrial accidents, financial and commodity market crashes, etc.), as well as phenomena for which natural and anthropogenic factors interact in complex ways (epidemic disease spread, global warming-related changes in climate and weather, etc.).

Overview

Rare events are discrete occurrences that are statistically “improbable” in that they are very infrequently observed. Despite being statistically improbable, such events are plausible insofar as historical instances of the event (or a similar event) have been documented.[2] Scholarly and popular analyses of rare events often focus on those events that could be reasonably expected to have a substantial negative impact on a society—either economically[3] or in terms of human casualties[4] (typically, both). Examples of such events might include an 8.0+ Richter magnitude earthquake, a nuclear incident that kills thousands of people, or a 10%+ single-day change in the value of a stock market index.[5][6][7]

Modeling and analysis

Rare event modeling (REM) refers to efforts to characterize the statistical distribution parameters, generative processes, or dynamics that govern the occurrence of statistically rare events, including but not limited to high-impact natural or human-made catastrophes. Such “modeling” may include a wide range of approaches, including, most notably, statistical models derived from historical event data and computational software models that attempt to simulate rare event processes and dynamics.[8] REM also encompasses efforts to forecast the occurrence of similar events over some future time horizon, which may be of interest for both scholarly and applied purposes (e.g., risk mitigation and planning).[9]

Relevant data sets

In many cases, rare and catastrophic events can be regarded as extreme-magnitude instances of more mundane phenomena. For example, seismic activity, stock market fluctuations, and acts of organized violence all occur along a continuum of extremity, with more extreme-magnitude cases being statistically infrequent.[10] Therefore, rather than viewing rare event data as its own class of information, data concerning “rare” events often exists as a subset of data within a broader parent event class (e.g., a seismic activity data set would include instances of extreme earthquakes, as well as data on much lower-intensity seismic events).

The following is a list of data sets focusing on domains that are of broad scholarly and policy interest, and where “rare” (extreme-magnitude) cases may be of particularly keen interest due to their potentially devastating consequences. Descriptions of the data sets are extracted from the source websites or providers.

See also

References

  1. ↑ King, G., & Zeng, L. (2001). Logistic regression in rare events data. Political Analysis, 9(2), 137–63. http://pan.oxfordjournals.org/content/9/2/137.short
  2. ↑ Morio, J., Balesdent, M. (2015). Estimation of Rare Event Probabilities in Complex Aerospace and Other Systems. Elsevier Science. http://store.elsevier.com/product.jsp?isbn=9780081000915&pagename=search
  3. ↑ Sanders, D. (2002). The management of losses arising from extreme events. Paper presented at General Insurance Convention. http://www.actuaries.org.uk/research-and-resources/documents/management-losses-arising-extreme-events
  4. ↑ Clauset, A., & Woodard, R. (2013). Estimating the historical and future probabilities of large terrorist events. Annals of Applied Statistics,7(4),1838-1865. doi:10.1214/12-AOAS614. http://arxiv.org/abs/1209.0089
  5. ↑ Ghil, M., P. Yiou, S. Hallegatte, B. D. Malamud, P. Naveau, A. Soloviev, P. Friederichs, et al. (2011). Extreme events: Dynamics, statistics and prediction. Nonlinear Processes in Geophysics, 18(3), 295–350. doi:10.5194/npg-18-295-2011. http://www.nonlin-processes-geophys.net/18/295/2011/npg-18-295-2011.pdf
  6. ↑ Sharma, A. S., Bunde, A., Dimri,V.P., & Baker,D.N. (2013). Extreme events and natural hazards: The complexity perspective. Wiley. https://books.google.com/books?id=t3F9K5clZwsC
  7. ↑ Watkins, N. W. (2013). Bunched black (and grouped grey) swans: Dissipative and non‐dissipative models of correlated extreme fluctuations in complex geosystems. Geophysical Research Letters, 40(2), 402–10
  8. ↑ Embrechts, P., Klüppelberg, C., & Mikosch, T. (1997). Modelling extremal events: For insurance and finance. (Vol. 33). Springer.
  9. ↑ Goodwin, P., & Wright,G. (2010). The limits of forecasting methods in anticipating rare events. Technological Forecasting and Social Change, 77(3), 355–68.
  10. ↑ Clauset, A., Shalizi, C., Newman, M.E.J. (2009). Power-law distributions in empirical data. SIAM Review (Society for Industrial and Applied Mathematics Publications), 51,(4), 661–703. doi:10.1137/070710111. Retrieved August 29, 2014. http://arxiv.org/abs/0706.1062
This article is issued from Wikipedia - version of the 11/3/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.