Estimating Conditional Quantiles for Financial Time Series by Bootstrapping and Subsampling Methods

Value at Risk (VaR) has become one of the most commonly used measures of risk for …nancial risk management. Econometrically, a suitable conditional quantile model can provide accurate estimation for this purpose. However due to the special dependence features of …nancial time series, a classical econometric methodology does not lend itself for this purpose . In this paper, the main objective is to combine bootstrap technique with nonparametric methodology to estimate the conditional quantile for …nancial time series. Three newly developed bootstrap based methods (nonparametric wild bootstrap, block bootstrapping and subsampling) are adopted, and local linear nonparametric estimation is then used for estimation. Moving block bootstrapping is applied to generate the con…dence intervals for the conditional quantile estimates. The performance of the models is evaluated by means of Monte Carlo simulations.