Bootstrap-Based Inference in Models with a Nearly Noninvertible Moving Average Component.

This article proposes a bootstrap method for constructing two-sided confidence intervals for the moving average (MA) parameter in nearly noninvertible models. The confidence intervals are obtained by inverting the acceptance region of the likelihood ratio (LR) test reflecting the asymmetry of the likelihood near the noninvertibility boundary. The limiting distribution of the LR statistic is nonpivotal and its quantiles are parameterized as a function of the MA parameter and then approximated by grid bootstrap. The proposed method is used to investigate the parameter instability in inflation and time variability of risk premium in interest rates.