Prof. Raphael Huser's group focuses on two aspects of extreme statistics:
- Development of statistical models and inference methods for extreme events. Although the methodology might be applied in a wide range of contexts, we are mainly interested in the modeling of complex environmental extremes, such as floods, heat waves, wind speeds, etc. Important questions include the characterization of space-time dependence at extreme levels, the modeling and estimation of non-stationarity (in space and time), and the development of efficient inference methods to fit these extremal models to real data.
- Development of efficient methods for large datasets. These include the development of inference approaches for complicated extremal models (e.g., composite likelihoods, local likelihoods, etc.), the joint modeling of multiple parallel time series, or the spatial prediction for large datasets.