Exchangeability, extreme returns and Value-at-Risk forecasts

In this paper, we propose a new approach to extreme value modelling for the forecasting of Value-at-Risk (VaR). In particular, the block maxima and the peaks-over-threshold methods are generalised to exchangeable random sequences. This caters for the dependencies, such as serial autocorrelation, of...

Full description

Bibliographic Details
Main Authors: Huang, Chun-Kai, North, D., Zewotir, T.
Format: Journal Article
Published: Elsevier BV * North-Holland 2017
Online Access:http://hdl.handle.net/20.500.11937/67319
_version_ 1848761534691409920
author Huang, Chun-Kai
North, D.
Zewotir, T.
author_facet Huang, Chun-Kai
North, D.
Zewotir, T.
author_sort Huang, Chun-Kai
building Curtin Institutional Repository
collection Online Access
description In this paper, we propose a new approach to extreme value modelling for the forecasting of Value-at-Risk (VaR). In particular, the block maxima and the peaks-over-threshold methods are generalised to exchangeable random sequences. This caters for the dependencies, such as serial autocorrelation, of financial returns observed empirically. In addition, this approach allows for parameter variations within each VaR estimation window. Empirical prior distributions of the extreme value parameters are attained by using resampling procedures. We compare the results of our VaR forecasts to that of the unconditional extreme value theory (EVT) approach and the conditional GARCH-EVT model for robust conclusions.
first_indexed 2025-11-14T10:33:12Z
format Journal Article
id curtin-20.500.11937-67319
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:33:12Z
publishDate 2017
publisher Elsevier BV * North-Holland
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-673192018-09-21T00:31:09Z Exchangeability, extreme returns and Value-at-Risk forecasts Huang, Chun-Kai North, D. Zewotir, T. In this paper, we propose a new approach to extreme value modelling for the forecasting of Value-at-Risk (VaR). In particular, the block maxima and the peaks-over-threshold methods are generalised to exchangeable random sequences. This caters for the dependencies, such as serial autocorrelation, of financial returns observed empirically. In addition, this approach allows for parameter variations within each VaR estimation window. Empirical prior distributions of the extreme value parameters are attained by using resampling procedures. We compare the results of our VaR forecasts to that of the unconditional extreme value theory (EVT) approach and the conditional GARCH-EVT model for robust conclusions. 2017 Journal Article http://hdl.handle.net/20.500.11937/67319 10.1016/j.physa.2017.02.080 Elsevier BV * North-Holland restricted
spellingShingle Huang, Chun-Kai
North, D.
Zewotir, T.
Exchangeability, extreme returns and Value-at-Risk forecasts
title Exchangeability, extreme returns and Value-at-Risk forecasts
title_full Exchangeability, extreme returns and Value-at-Risk forecasts
title_fullStr Exchangeability, extreme returns and Value-at-Risk forecasts
title_full_unstemmed Exchangeability, extreme returns and Value-at-Risk forecasts
title_short Exchangeability, extreme returns and Value-at-Risk forecasts
title_sort exchangeability, extreme returns and value-at-risk forecasts
url http://hdl.handle.net/20.500.11937/67319