Peaks Over Thresholds Modeling With Multivariate Generalized Pareto Distributions

Anna Kiriliouk, Holger Rootzén, Johan Segers, Jennifer L. Wadsworth

Research output: Contribution to journalArticlepeer-review

37 Downloads (Pure)

Abstract

When assessing the impact of extreme events, it is often not just a single component, but the combined behaviour of several components which is important. Statistical modelling using multivariate generalized Pareto (GP) distributions constitutes the multivariate analogue of univariate peaks over thresholds modelling, which is widely used in finance and engineering. We develop general methods for construction of multivariate GP distributions and use them to create a variety of new statistical models. A censored likelihood procedure is proposed to make inference on these models, together with a threshold selection procedure, goodness-of-fit diagnostics, and a computationally tractable strategy for model selection. The models are fitted to returns of stock prices of four UK-based banks and to rainfall data in the context of landslide risk estimation. Supplementary materials and codes are available online.
Original languageEnglish
Pages (from-to)123-135
JournalTechnometrics
Volume61
Issue number1
DOIs
Publication statusPublished - 2 Jan 2019
Externally publishedYes

Keywords

  • Financial risk
  • Landslides
  • Multivariate extremes
  • Tail dependence

Fingerprint

Dive into the research topics of 'Peaks Over Thresholds Modeling With Multivariate Generalized Pareto Distributions'. Together they form a unique fingerprint.

Cite this