The risk management functions of most financial institutions occupy themselves with the estimation of the value at risk (VaR) of their portfolios as a measure of market risk. Various methods are available to calculate the VaR measure, and this can be done at various degrees of confidence. This study evaluates and analyses the performance of five popular VaR forecasting methods in the South African context, using the closing values of three of the major indices available on the Johannesburg Stock Exchange (JSE), namely the All Share Index (ALSI), the Financials-Industrials Index (FINDI), and the Resources Index (RESI). These three indices are considered based on the findings of prior studies that indicate that not only does decomposing the ALSI into its constituent (the FINDI and the RESI) indices provide a better measurement of market risk on the JSE, but these sub-indices also have different systematic risk exposures which may necessitate different treatments in measuring their risks appropriately. The periods examined surrounded the 2008 global financial crisis in order to allow an evaluation of the impact of varying levels of volatility on the analysis. Overall, the study concludes that the performance of the VaR models examined is similar when assessing the risk of the ALSI and the RESI returns, while they are very different for the FINDI. This conclusion provides crucial insight into the risk management and investment decisions concerning portfolios which are more heavily invested in the FINDI as opposed to the other two, as this study suggests that a blanket treatment to the South African market is incorrect.
| Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:uct/oai:localhost:11427/32693 |
| Date | 26 January 2021 |
| Creators | Gross, Eden |
| Contributors | Kruger, Ryan |
| Publisher | Faculty of Commerce, Department of Finance and Tax |
| Source Sets | South African National ETD Portal |
| Language | English |
| Detected Language | English |
| Type | Master Thesis, Masters, MCom |
| Format | application/pdf |
Page generated in 0.0011 seconds