A comparative VaR analysis between low-frequency and high-frequency conditional EVT models during COVID-19 crisis

Citation

Aridi, Nor Azliana and Tan, Siow Hooi and Chin, Wen Cheong (2024) A comparative VaR analysis between low-frequency and high-frequency conditional EVT models during COVID-19 crisis. Cogent Economics & Finance, 12 (1). ISSN 2332-2039

[img] Text
A comparative VaR analysis between low-frequency and high-frequency conditional EVT models during CO.pdf - Published Version
Restricted to Repository staff only

Download (2MB)

Abstract

The aim of this paper is to assess whether the availability of high-frequency data enhan-ces the accuracy of extreme market risk estimation in comparison to low-frequency databy using Value-at-risk (VaR) and Expected shortfall (ES). The sample data used for ana-lysis comprised the daily closing stock prices and 5-minute intraday stock prices of DJIA,FTSE100, BOVESPA, and MERVAL Index from 2014 to 2022. The data analysis was doneto compare the performance of two-stages hybrid methods called conditional EVT thatcombined the GARCH, RV and HAR specification models with the EVT approach. Toassess the accuracy of the VaR forecasts, out-of-sample VaR forecast was backtested byusing unconditional coverage (UC) and conditional coverage (CC) tests. The VaR back-testing procedure also incorporated the utilization loss function which are the regula-tory loss function (RLF) and the firm’s loss function (FLF). The accuracy of the forecastedES was backtested by using the generalized breach indicator (GBI) method. The findingsof this research emphasized that high-frequency conditional EVT, incorporating the HARspecification outperformed the low-frequency conditional EVT in predicting market riskduring periods characterized by extreme returns. Based on the VaR and ES measure, theHAR-EVT typed models are the best performance model compared to the GARCH-EVTand RV-EVT typed models during both crisis and non-crisis periods. This research studycontributes to the current literature on the forecasting ability of risk models by concen-trating on the hybrid model of long-memory models (FIEGARCH, RV-FIEGARCH andHAR-FIEGARCH) for with the EVT approach

Item Type: Article
Uncontrolled Keywords: High-frequency data
Subjects: H Social Sciences > HF Commerce > HF5001-6182 Business > HF5410-5417.5 Marketing. Distribution of products
Divisions: Faculty of Management (FOM)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 31 Jul 2024 03:16
Last Modified: 31 Jul 2024 03:16
URII: http://shdl.mmu.edu.my/id/eprint/12667

Downloads

Downloads per month over past year

View ItemEdit (login required)