Estimating Parameters of SAR Model by Recursive Least Square Method

Abstract

Seasonal runoff series can be described by seasonal autoregressive model, which is extensively applied in long-term runoff forecasting. The common way of parameters estimation is moment estimation. This paper estimates parameters of seasonal autoregressive model by recursive least square method and applies the method in forecasting the monthly runoff for the Three Gorges. An effective procedure based upon the least fitting error is proposed to determine the model order. The forecasting results are satisfactory.