Assessing the relative performance of heavy-tailed distributions: Empirical evidence from the Johannesburg stock exchange
MetadataShow full item record
It has been well documented that the empirical distribution of daily logarithmic returns from financial market variables is characterized by excess kurtosis and skewness. In order to capture such properties in financial data, heavy-tailed and asymmetric distributions are required to overcome shortfalls of the widely exhausted classical normality assumption. In the context of financial forecasting and risk management, the accuracy in modeling the underlying returns distribution plays a vital role. For example, risk management tools such as value-at-risk (VaR) are highly dependent on the underlying distributional assumption, with particular focus being placed at the extreme tails. Hence, identifying a distribution that best captures all aspects of the given financial data may provide vast advantages to both investors and risk managers. In this paper, we investigate major financial indices on the Johannesburg Stock Exchange (JSE) and fit their associated returns to classes of heavy tailed distributions. The relative adequacy and goodness-of-fit of these distributions are then assessed through the robustness of their respective VaR estimates. Our results indicate that the best model selection is not only variant across the indices, but also across different VaR levels and the dissimilar tails of return series.
Showing items related by title, author, creator and subject.
Zhao, X.; Scarrott, C.; Oxley, Leslie; Reale, M. (2010)This article introduces a new approach for estimating Value at Risk (VaR), which is then used to show the likelihood of the impacts of the current financial crisis. A commonly used two-stage approach is taken, by combining ...
Chinhamu, K.; Huang, Chun-Kai; Huang, C.; Hammujuddy, J. (2015)© 2014 Economic Society of South Africa. While the classical normality assumption is simple to implement, it is well known to underestimate the leptokurtic behaviour demonstrated in most financial data. After examining ...
Laker, I.; Huang, Chun-Kai; Clark, A. (2017)Estimation in extreme financial risk is often faced with challenges such as the need for adequate distributional assumptions, considerations for data dependencies, and the lack of tail information. Bootstrapping provides ...