Peaks over thresholds modelling with multivariate generalized Pareto distributions

Kiriliouk, Anna and Rootzén, Holger and Segers, Johan and Wadsworth, Jennifer Lynne (2019) Peaks over thresholds modelling with multivariate generalized Pareto distributions. Technometrics, 61 (1). pp. 123-135. ISSN 0040-1706

[thumbnail of KRSW-Technometrics]
Preview
PDF (KRSW-Technometrics)
KRSW_Technometrics.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.

Download (1MB)

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.

Item Type:
Journal Article
Journal or Publication Title:
Technometrics
Additional Information:
This is an Accepted Manuscript of an article published by Taylor & Francis in Technometrics on 19/04/2018, available online: http://www.tandfonline.com/10.1080/00401706.2018.1462738
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/2600/2611
Subjects:
?? financial risklandslidesmultivariate extremestail dependencemodelling and simulationapplied mathematicsstatistics and probability ??
ID Code:
124333
Deposited By:
Deposited On:
03 Apr 2018 13:06
Refereed?:
Yes
Published?:
Published
Last Modified:
15 Sep 2024 00:30