This editorial essay concerns the use (or lack thereof) of the statistics of extremes in climate change research. So far, the statistical theory of extreme values has been primarily applied to climate under the assumption of stationarity. How this theory can be applied in the context of climate change, including implications for the analysis of the economic impacts of extremes, is described. Future research challenges include the statistical modeling of complex extreme events, such as heat waves, and taking into account spatial dependence in the statistical modeling of extremes for fields of climate observations or of numerical model output. Addressing these challenges will require increased collaboration between climate scientists and statisticians.
KeywordsHeat Wave Extreme Event Climate Change Research Block Maximum Generalize Pareto
Unable to display preview. Download preview PDF.
- Coles S (2001) An introduction to statistical modeling of extreme values. Springer, LondonGoogle Scholar
- Davison AC, Smith RL (1990) Models for exceedances over high thresholds. J R Stat Soc, B 52:393–442Google Scholar
- Embrechts P, Klüppelberg C, Mikosch T (1997) Modelling extremal events for insurance and finance. Springer, BerlinGoogle Scholar
- Gumbel EJ (1958) Statistics of extremes. Columbia University Press, New YorkGoogle Scholar
- Wigley TML (1985) Impact of extreme events. Nature 316:106–107Google Scholar
- Wigley TML (1988) The effect of changing climate on the frequency of absolute extreme events. Clim Monit 17:44–55 (reprinted in Climatic Change (2009) 97:67–76)Google Scholar