Multistep Yule-walker estimation of autoregressive models

Abstract

The aim of this work is to fit a ?wrong? model to an observed time series by employing higher order Yule-Walker equations in order to enhance the fitting accuracy. Several parameter estimation methods for autoregressive models were reviewed, such as Maximum Likelihood method, Least Square method, Yule-Walker method, Burg?method, etc. Comparison of the estimation accuracy between the well-known Yule-Walker method and our new multistep Yule-Walker method based on the autocorrelation function (ACF) is made. The effect of different number of Yule-Walker equations on the estimation performance is investigated. Monte Carlo analysis and real data are used to check the performance of the proposed method.