Timeseries Analysis using AR, MA, and ARMA models

We have already used auto-correlation function (ACF) and auto-regressive (AR) models in Sections 5.2.2, 5.2.5, 5.2.8, and 5.3.3. In this chapter, we go into more detail and describe a broader set of methods for feature extraction and parameter estimation for stationary time-series models with rational spectra, a class to which AR processes belong. We also compare the methods in section 10.4.10.