Environmental ExtremesOrganised by the Environmental Statistics Section of the Royal Statistical Society.Thursday 2 December 2010 (10:30am - 4pm)RSS, 12 Errol Street, London, EC1Y 8LX |
---|
For both statisticians and their scientific colleagues, this meeting will provide introductions to the statistics for analyzing extreme events along with research examples of their application within environmental science.
Please use the form available here to register.
Please contact Ron Smith for further details.
- Statistics of extremes: An overview
- An overview of Dependence Modelling in Multivariate Extremes
- Marginal modelling of spatially-dependent non-stationary extremes using threshold modelling
- Spatial extremes
You need not be a member of the Royal Statistical Society to attend, but registration will be required.
Registration fees, which cover lunch and refreshments, are as follows:
The meeting will take place at the Royal Statistical Society, 12 Errol Street, London, EC1Y 8LX.
Directions can be found here
This first talk will sketch elements of statistics of extremes, including probability models and statistical inference for extremes of independent and dependent data, regression modelling and non-stationarity.
For problems where interest is estimation of the extremal behaviour of combinations of dependent variables, multivariate extreme theory provides a range of asymptotically motivated dependence measures and modelling approaches. In this talk we will outline the key existing methods and suggest a new approach that bridges the gap between the two most widely used.
It is common for environmental extremes to exhibit non-stationary behaviour. We consider the use of quantile regression to set a covariate-dependent threshold for extreme value modelling. As an example we present the marginal modelling of wave heights, for which adjustment for spatial dependence is necessary.
The second talk will give an overview of models for spatial extreme-value modelling. Examples of application to data will be included.