M-regression spectral estimator for periodic ARMA models. An empirical investigation

The M-regression estimator has recently been widely used to build spectral estimators in time series models. In this paper, we extend approach when the data follow a periodic autoregressive moving average process. We introduce an of parameters based on classical Whittle estimator. finite sample size performances proposed are analyzed under scenarios PARMA processes with and without additive outliers. Under non-contaminated scenario, our maximum Gaussian likelihood have similar behaviors. However, contaminated case, two last severely biased, while is robust. As real application, carbon monoxide concentrations analyzed. A model fitted forecasted model.