Abstract. In this paper we propose a new forecasting methodology that comprises simultaneous level-wise modeling in the wavelet domain. The WAW methodology (short for wavelet-armax-winters) uses three modeling startegies: ARMAX models capable of incorporating external inputs and model feedbacks, trigonometric regressions sensitive to seasonality effects and Holt-Winters models describing trends...

Autoregressive moving average systems with exogenous inputs (ARMAX) are widely used in a variety of applied problems connected with identification, adaptive control and time series analysis. This paper proposes the method which enables one to estimate parameters in the ARMAX system with a prescribed mean-square precision at the termination time. The procedure is constructed on the basis of sequ...

Short-term management of groundwater resources, especially during droughts, can be assisted by forecasts of groundwater levels. Such forecasts need to account for the natural dynamic behaviour of the aquifer, likely recharge scenarios, and recent but unknown abstractions. These requirements mean that forecasts, at say monthly intervals, need to be updated with current observations on a real-tim...

The needs of accuracy of machines are strictly increasing for the manufacturing processes. It is costly to use high precision machine to achieve the goal. Therefore, if the forecasting of errors can be obtained from the gathered past error values, it allows the control system to compensate the errors. In this paper, the simulations of manufacturing processes are using the ARMA and ARMAX models....

Experimental methods used to determine the dynamic behaviour of helicopter structures can be broadly categorised as either ground testing methods or in-flight testing methods. A major limitation of ground testing is that dynamic properties determined from a grounded helicopter structure are usually significantly influenced by the boundary conditions. Therefore, it is desirable to carry out test...

This paper gives an expression for the minimum mean squared error predictor of the single equation ARMAX model when all the parameters are known. A formula is then derived for the asymptotic prediction mean squared error when the parameters are replaced by their maximum likelihood estimates. These general results are then specialised to the regression model with ARMA errors; for this case we al...