Bootstrapping ARMA Models: Some Simulations

The bootstrap is used to demonstrate the feasibility of obtaining estimates of standard errors of the parameter estimates of ARMA models. The method is applied to simulated data and to two published data sets, and the success of the bootstrap is evaluated. The simulations show the bootstrap to be an effective tool for estimating standard errors for parameter estimates in time series models. The bootstrap estimates of the standard errors are distribution free and valid for small samples.