| Summary: | With the rapid growth of the increasingly complex trading activities and financial market instability, there is a growing concern of financial risk management throughout the China's stock market. One widely adopted technique to manage risk involves the use of Value-at-Risk (VaR), which is known as the benchmark for quantifying market risk. In the past few years, it has been widely accepted by both practitioners and regulators as the right way to measure risks. The concept of VaR describes the loss that can occur over a given time horizon, at a given confidence level, due to exposure to market risk. However, the use of VaR as a risk measurement is just at the early stages in China's stock market. Thus, this dissertation is dedicated to explain how to estimate VaR of Chinese Stock Index by using the three main approaches (Historical Simulation, GARCH volatility model and Filtered Historical Simulation), and discuss their advantages and limitations as well. Backtesting is conducted to check which VaR forecasting model is more appropriate for China's stock market.
|
|---|