A sieve bootstrap scheme, the Neural Network Sieve bootstrap, for nonlinear time series is discussed. The approach, which is non parametric in its spirit, does not have the preoblems of other nonparametric bootstrap techniques. The procedure is used to construct predition intervals and it takes into account the uncertainty associated with the estimation of the model parameters. An application to real data sets is also presented.
File in questo prodotto:
Non ci sono file associati a questo prodotto.