Empirical Likelihood Test for Stationary Short Memory Time Series Models

In this paper, we propose empirical likelihood method for parameter hypothesis test in short memory time series models. In practice, we may pay attention to not only the significance of all the parameters, but also the significance of some parameter in the models. So we construct different test statistics in these two situations, which are both shown to follow chi-square distributions asymptotically. In addition, our simulations investigate the power function for testing the concerned parameters and verify the validity of the proposed testing procedure.