Empirical study for exchange rate risk of CNY: Using VaR and ES based on extreme value theory

This paper applies extreme value theory (EVT) to estimate return seriespsila tails of CNY exchange rates, and finds that the degree of fitting Pareto distribution to the data of return seriespsila tail is extremely high; whatpsilas different from expected result is that expected shortfall (ES) canpsilat improve the tail risk problem of Value-at-Risk (VaR) evidently. Result of back testing indicates that EVT-based VaR values underestimate the risk of USD/CNY and HKD/CNY, this may be caused by the continuous CNY appreciation toward USD and HKD. However, comparing with VaR values calculated by historical simulation (HS) and variance-covariance method, VaR values calculated by EVT can measure the risk more accurately while dealing with JPY/CNY and EUR/CNY under high confidence level.