Spectral estimation in the presence of missing data

In this article we propose a quasi-Whittle estimator for parametric families of time series models in the presence of missing data. This estimator extends results to the incompletely observed case. This extension is valid to non-Gaussian and nonlinear models. It also allows us to bound the variance of an associated quasiperiodogram. A simulation study empirically validates the proposed estimate for mixing and nonmixing models.