Methods to compute linear h-step ahead prediction coefficients based on localised and iterated Yule-Walker estimates and empirical mean squared and absolute prediction errors for the resulting predictors. Also, functions to compute autocovariances for AR(p) processes, to simulate tvARMA(p,q) time series, and to verify an assumption from Kley et al. (2017), Preprint < http://personal.lse.ac.uk/kley/forecastSNSTS.pdf>.
o Added MAPE function. o Added parameters trimLo and trimUp to MSPE function.
o Fixed a small bug in function f and corresponding example.
o Added function acfARp to compute autocovariances of AR(p) processes. o Added function f that can be used to verify assumption (10) from Theorem 3.1 in Kley et al. (2016).
o two functions to compute linear prediction coefficients and mean squared prediction errors. o demo on how to analyse, using a simulated tvARMA(1,1) time series