Daily Value-at-Risk models at financial crisis period: evidence in Australia
Over the past decades portfolio and risk management techniques had adapted to increasingly complex financial instrument. Within the different forms of financial risk measurement tools, Value at Risk (VAR) which provides the most expediency measurement from the adverse market movements, is now widely accepted as a fundamental tool for risk management and it has become a standard benchmark for measuring financial risk since the 1990s. This dissertation primarily focuses on using the newly created Australian implied volatility as an input for Value-at-Risk models during the financial crisis period and then compares the testing results with other two different volatility inputs based on two back-testing methods. The results show that during the financial crisis period straight forward volatility forecasts based on Australian implied volatility do not provide meaningful volatility information in VAR models, and this was however fine in most cases when using RiskMetrics and GJR-GARCH as volatility forecasts methods. This indicates that the models’ performances can be deteriorating in challenging trading environments, and in order to get protection against credit risk, operational risk and liquidity risk, the risk managers or investors should appropriate use of VAR.