Analysing the Multiscale Systematic Risk During the Global Financial Crisis: Evidence from Selected European Stock Markets

Alexandridis, Antonis, Hasan, Mohammad S (2015) Analysing the Multiscale Systematic Risk During the Global Financial Crisis: Evidence from Selected European Stock Markets. In: 14th Hellenic Finance and Accounting Association. . (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)

Abstract

In this paper, we have investigated the impact of the global financial crisis on the multi-horizon nature of systematic risk and market risk using daily data of eight major European equity markets over the period of 2005-2012. The method is based on a wavelet multiscale approach within the framework of a capital asset pricing model. The sample covers pre-crisis, crisis and post-crisis periods with varying experiences and regimes. First we investigate for possible contagion effects of the U.S. crisis to the European stock markets and then we perform a local analysis of each European stock market separately. Empirical results demonstrate that beta coefficients have a multiscale tendency in sample countries and betas tend to increase at higher scale (lower frequencies) for the whole period. However, the size of betas and R2s tend to increase during the crisis period compared to the pre-crisis period. The multiscale nature of the betas is consistent with the fact that stock market investors have different time horizons due to different trading strategies. Our results based on scale dependent value at risk (VaR) suggest that market risk tends to be more concentrated at lower time scale (higher frequencies) of the data. Moreover, the scale-by-scale estimates of VaR have increased almost three fold for every market during the crisis period compared to the pre-crisis period. Finally, we have presented an approach for accurately forecasting time-dependent betas and VaR using wavelet networks.

Item Type: Conference or workshop item (Paper)
Subjects: H Social Sciences > HG Finance
Divisions: Faculties > Sciences > School of Mathematics Statistics and Actuarial Science
Faculties > Sciences > School of Mathematics Statistics and Actuarial Science > Actuarial Science
Depositing User: Mohammad Hasan
Date Deposited: 28 Dec 2015 10:46 UTC
Last Modified: 29 May 2019 16:50 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/53563 (The current URI for this page, for reference purposes)
  • Depositors only (login required):