Dynamic nonparametric filtering with application to volatility estimation

Problems of nonparametric filtering arises frequently in engineering and financial economics. Nonparametric filters often involve some filtering parameters to choose. These parameters can be chosen to optimize the performance locally at each time point or globally over a time interval. In this article, the filtering parameters are chosen via minimizing the prediction error for a largo class of filters. Under a general martingale setting, with mild conditions on the time series structure and virtually no assumption on filters, we show that the adaptive filter with filtering parameter chosen by historical data performs nearly as well as the one with the ideal filler in the class, in terms of filtering errors. The theoretical result is also verified via intensive simulations. Our approach is also useful for choosing the orders of parametric models such as AR or GARCH processes. It can also be applied to volatility estimation in financial economics. We illustrate the proposed methods by estimating the volatility of the returns of the S&P500 index and the yields of the three-month Treasury hills.