Bandwidth selection by cross-validation for forecasting long memory financial time series

Abstract

The paper addresses the issue of choice of bandwidth in the application of semiparametric estimation of the long memory parameter in a univariate time series process. The focus is on the properties of forecasts from the long memory model. A variety of cross-validation methods based on out of sample forecasting properties are proposed. These procedures are used for the choice of bandwidth and subsequent model selection. Simulation evidence is presented that demonstrates the advantage of the proposed new methodology. • The optimal bandwidth in the estimation of the long memory parameter is examined. • Various cross-validation methods are used. • The bandwidth that provides better forecasts is selected. • The results confirm the properties and applicability of the method. • The results indicate that the method improves the filtering of long memory series.