Suggested Papers for STAT 548 (2023/2024)

Below are suggestions of papers for the qualifying course. These papers aim to address a variety of questions in the field of multivariate extreme value theory. As is typical in this area, the papers tend to first develop probabilistic results for extremes, which are then used to motivate a statistical methodology and apply it to real data.

I expect reports to be 10-15 pages long and to clearly convey main ideas of the chosen paper, an illustration of the proposed methodology followed by a discussion of limitations and potential extensions of the proposed method(s).

M. Meerschaert, H.-P. Scheffler and S. Stoev (2013). Extreme value theory with operator norming. Extremes 16: 407-428.

This paper has a heavy theoretical component. However, large parts of it can be omitted. I would be interested in the implementation of the proposed methodology to test for hetero-ouracity (different tail indices across different directions).

Debbie J. Dupuis, Sebastian Engelke, Luca Trapin (2023). Modeling panels of extremes. Ann. Appl. Stat. 17(1): 498-517.

The supplement to this paper discusses an alternative model, a grouped panel generalized Pareto model. A project could focus on this extension.

Y. He and J. Einmahl (2017). Estimation of extreme depth-based quantile regions. J. R. Statist. Soc. B. 79: 449-461.

Beranger, B., Padoan, S.A. & Sisson, S.A (2019). Estimation and uncertainty quantification for extreme quantile regions. Extremes, https://doi.org/10.1007/s10687-019-00364-0.

Vignotto, E., Engelke, S. Extreme value theory for anomaly detection - the GPD classifier. Extremes 23, 501-520 (2020). https://doi.org/10.1007/s10687-020-00393-0

C. Rohrbeck and D. Cooley (2021). Simulating flood event sets using extremal principal components. Ann. Appl. Stat. 17(2): 1333-1352.

J.L. Wadsworth et al. (2016). Modelling across extremal dependence classes. J. R. Statist. Soc. B. 79: 149-175.

C. Scott and R. Nowak (2005). Learning Minimum Volume Sets. Advances in Neural Information Processing Systems 18.